Xentir LIVE INTELLIGENCE · data updated automatically
AI Model Rankings
Updated
Live benchmark results, sourced from published third-party evaluations. Reference pricing is read directly from OpenAI, Anthropic and Google's own published price pages where a model has one; inference speed has no licensed or self-measured source yet — see the empty card below rather than a guess.
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-21 · Methodology · Data Sources · Ranking changes
Benchmark results measure specific tasks and should not be treated as a universal measure of model quality.
Best Overall
GPT-6 Astra
Highest Epoch Capabilities Index (ECI) score.
166.3 ECI
Best Coding
Claude Opus 4.7
Highest score on SWE-bench Verified.
0.835 (max) SWE-bench
Best Reasoning
GPT-6 Astra
Highest score on GPQA Diamond.
0.958 (max) GPQA
Best Open Model
Kimi K3
Highest ECI among open-weight models.
157.6 ECI
Fastest
Not measured yet
We do not measure inference speed yet — no licensed or self-generated latency data exists. Not shown as an estimate.
Lowest Output Price
GPT-5 nano
Lowest published output-token price among Epoch-evaluated models with vendor pricing on file.
$0.40 /1M tokens (output)
price as published by OpenAI, checked 2026-09-20
Compare models
Pick up to four models and see every benchmark side by side. Type to search; the best value in each row is marked. The list refreshes automatically with every data update.
Show more columns
Scroll to see more →
| Rank | Model | Provider | Overall | Coding | Reasoning | Released | Price |
|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | 166.3 | — | 0.958 (max) | 2026-09 | $10.00 / $50.00 |
| 2 | Claude Fable 5.1 | Anthropic | 164.5 | — | — | 2026-09 | — |
| 3 | Claude Fable 5 | Anthropic | 163.3 | — | 0.859 (max) | 2026-06 | $10.00 / $50.00 stale |
| 4 | Claude Opus 5 | Anthropic | 162.3 | — | 0.939 (max) | 2026-07 | $5.00 / $25.00 stale |
| 5 | GPT-5.5 Pro | OpenAI | 162.2 | — | 0.939 (xhigh-pre-release) | 2026-04 | $30.00 / $180.00 |
| 6 | GPT-5.6 Sol | OpenAI | 161.8 | — | 0.935 (max) | 2026-07 | $4.00 / $20.00 |
| 7 | GPT-5.6 Terra | OpenAI | 159.1 | — | 0.933 (max) | 2026-07 | $2.00 / $12.00 |
| 8 | GPT-5.5 | OpenAI | 159.1 | 0.806 (xhigh-pre-release) | 0.940 (xhigh-pre-release) | 2026-04 | $5.00 / $30.00 |
| 9 | GPT-5.4 Pro | OpenAI | 158.9 | — | 0.946 (xhigh) | 2026-03 | $30.00 / $180.00 |
| 10 | Claude Opus 4.8 | Anthropic | 158.3 | — | 0.910 (max) | 2026-05 | $5.00 / $25.00 stale |
| 11 | Kimi K3 OPEN | Moonshot | 157.6 | — | 0.931 (max) | 2026-07 | — |
| 12 | Gemini 3.7 Flash | Google DeepMind | 157.4 | — | 0.948 (high) | 2026-08 | — |
| 13 | GPT-5.4 | OpenAI | 156.9 | 0.769 (high) | 0.933 (xhigh) | 2026-03 | $2.50 / $15.00 |
| 14 | Qwen 3.8 Max | Alibaba | 156.6 | — | 0.927 (xhigh) | 2026-08 | — |
| 15 | GPT-5.3 Codex | OpenAI | 156.6 | 0.748 (high) | — | 2026-02 | — |
| 16 | Gemini 3.8 Flash | Google DeepMind | 156.5 | — | 0.954 (high) | 2026-09 | — |
| 17 | Grok 4.6 | xAI | 156.3 | — | 0.940 (high) | 2026-08 | — |
| 18 | Claude Opus 4.7 | Anthropic | 156.3 | 0.835 (max) | 0.902 (xhigh) | 2026-04 | $5.00 / $25.00 stale |
| 19 | GPT-5.6 Luna | OpenAI | 156.3 | — | 0.916 (max) | 2026-07 | $0.20 / $1.20 |
| 20 | Claude Sonnet 5 | Anthropic | 156.2 | — | 0.905 (xhigh) | 2026-06 | $2.00 / $10.00 stale |
| 21 | Muse Spark 1.2 | Meta AI | 155.5 | — | — | 2026-08 | — |
| 22 | DeepSeek V4 Pro 0813 OPEN | DeepSeek | 155.5 | — | 0.917 (max) | 2026-08 | — |
| 23 | GPT-5.2 Pro | OpenAI | 155.4 | — | — | 2025-12 | $21.00 / $168.00 |
| 24 | Claude Opus 4.6 | Anthropic | 155.3 | 0.772 | 0.905 (32k) | 2026-02 | $5.00 / $25.00 stale |
| 25 | GLM-5.3 | Z.ai (Zhipu AI) | 155.2 | — | 0.909 (max) | 2026-08 | — |
| 26 | Qwen3.8 Max (0902) | Alibaba | 155.2 | — | 0.923 (xhigh) | 2026-09 | — |
| 27 | Gemini 3.1 Pro | Google DeepMind | 155.0 | 0.756 (customtools) | 0.944 (high) | 2026-02 | — |
| 28 | Gemini 3.5 Flash | Google DeepMind | 154.7 | 0.793 (high) | 0.928 (high) | 2026-05 | $1.50 / $9.00 |
| 29 | Muse Spark 1.1 | Meta AI | 154.6 | — | — | 2026-07 | — |
| 30 | DeepSeek V4 Flash 0731 OPEN | DeepSeek | 154.5 | — | 0.910 (max) | 2026-07 | — |
| 31 | Gemini 3.6 Flash | Google DeepMind | 154.3 | — | 0.941 (high) | 2026-07 | — |
| 32 | Grok 4.5 | xAI | 153.9 | — | 0.934 (high) | 2026-07 | — |
| 33 | Qwen3.7-Max | Alibaba | 153.7 | 0.773 | 0.909 | 2026-05 | — |
| 34 | GPT-5.2 | OpenAI | 153.5 | 0.738 (high) | 0.914 (xhigh) | 2025-12 | $1.75 / $14.00 |
| 35 | Gemini 3 Pro | Google DeepMind | 153.0 | 0.729 | 0.926 | 2025-11 | — |
| 36 | Claude Sonnet 4.6 | Anthropic | 152.2 | 0.752 | 0.874 (32k) | 2026-02 | $3.00 / $15.00 stale |
| 37 | Muse Spark | Meta AI | 152.1 | — | 0.898 | 2026-04 | — |
| 38 | Grok 4.20 | xAI | 152.0 | — | — | 2026-02 | — |
| 39 | Grok 4.20 (0309 Reasoning) | xAI | 152.0 | — | 0.893 | 2026-02 | — |
| 40 | GLM-5.2 OPEN | Z.ai (Zhipu AI) | 151.9 | 0.787 (max) | 0.919 (max) | 2026-06 | — |
| 41 | Gemini 3 Flash | Google DeepMind | 151.8 | 0.754 | 0.894 (high) | 2025-12 | — / $3.00 |
| 42 | GLM-5.3-Flash OPEN | Z.ai (Zhipu AI) | 151.4 | — | 0.902 (max) | 2026-08 | — |
| 43 | Kimi K2.6 OPEN | Moonshot | 151.0 | 0.767 | 0.908 | 2026-04 | — |
| 44 | GPT-5 Pro | OpenAI | 150.3 | — | — | 2025-10 | $15.00 / $120.00 |
| 45 | Inkling-Small OPEN | Thinking Machines | 150.2 | — | 0.885 (xhigh) | 2026-07 | — |
| 46 | Claude Opus 4.5 | Anthropic | 150.1 | 0.767 | 0.860 (32k) | 2025-11 | $5.00 / $25.00 stale |
| 47 | Kimi K2.7 Code OPEN | Moonshot | 150.1 | — | 0.879 | 2026-06 | — |
| 48 | GPT-5 (07 Aug 2025) | OpenAI | 150.0 | 0.736 (high) | 0.862 (high) | 2025-08 | — |
| 49 | GPT-5 (Chat) | OpenAI | 150.0 | — | — | 2025-08 | — |
| 50 | GLM-5.1 OPEN | Z.ai (Zhipu AI) | 149.7 | 0.742 | 0.899 | 2026-04 | — |
| 51 | GPT-5.1 | OpenAI | 149.6 | 0.669 (high) | 0.876 (high) | 2025-11 | $1.25 / $10.00 |
| 52 | Qwen 3.6 Max (Preview) | Alibaba | 149.3 | 0.767 | 0.874 | 2026-04 | — |
| 53 | Grok 4.3 Beta | xAI | 149.2 | — | 0.888 (high) | 2026-04 | — |
| 54 | DeepSeek-V4-Pro OPEN | DeepSeek | 149.1 | 0.776 (max) | 0.909 (high) | 2026-04 | — |
| 55 | GPT-5.4 Mini | OpenAI | 149.0 | — | 0.869 (xhigh) | 2026-03 | $0.75 / $4.50 |
| 56 | Inkling OPEN | Thinking Machines | 148.6 | — | 0.883 (xhigh) | 2026-07 | — |
| 57 | Kimi K2.5 OPEN | Moonshot | 148.0 | 0.738 | 0.876 (fireworks) | 2026-01 | — |
| 58 | Qwen 3.6 Plus | Alibaba | 147.7 | 0.579 | 0.884 | 2026-03 | — |
| 59 | o3-pro | OpenAI | 147.4 | — | — | 2025-06 | $20.00 / $80.00 |
| 60 | Qwen3.7-Plus | Alibaba | 147.4 | — | 0.879 | 2026-06 | — |
| 61 | Qwen3.5 397B-A17B OPEN | Alibaba | 147.0 | — | 0.864 (none) | 2026-02 | — |
| 62 | o3 | OpenAI | 146.9 | 0.623 (medium) | 0.818 (high) | 2025-04 | $2.00 / $8.00 |
| 63 | Claude Sonnet 4.5 | Anthropic | 146.8 | 0.713 | 0.823 (59k) | 2025-09 | $3.00 / $15.00 stale |
| 64 | Qwen 3.5 Plus (hosted 397B-A17B) | Alibaba | 146.7 | — | 0.848 | 2026-02 | — |
| 65 | MiniMax-M2.5 OPEN | MiniMax | 146.5 | — | — | 2026-02 | — |
| 66 | Qwen3.6 27B OPEN | Alibaba | 146.5 | — | 0.859 | 2026-04 | — |
| 67 | MiniMax-M3 OPEN | MiniMax | 146.5 | — | 0.909 | 2026-06 | — |
| 68 | Grok 4 | xAI | 146.4 | — | 0.870 | 2025-07 | — |
| 69 | Nemotron 3 Ultra OPEN | NVIDIA | 146.3 | — | 0.854 | 2026-06 | — |
| 70 | DeepSeek-V3.2 (Chat) OPEN | DeepSeek | 146.2 | — | 0.712 | 2025-12 | — |
| 71 | DeepSeek-V3.2 (Reasoner) OPEN | DeepSeek | 146.2 | — | 0.834 | 2025-12 | — |
| 72 | DeepSeek-V4-Flash OPEN | DeepSeek | 146.1 | — | — | 2026-04 | — |
| 73 | GLM-5 OPEN | Z.ai (Zhipu AI) | 145.8 | 0.721 | 0.878 | 2026-02 | — |
| 74 | GPT-5.4 Nano | OpenAI | 145.8 | — | 0.785 (high) | 2026-03 | $0.20 / $1.25 |
| 75 | MiniMax-M2.7 OPEN | MiniMax | 145.8 | — | — | 2026-03 | — |
| 76 | Kimi K2 Thinking OPEN | Moonshot | 145.8 | — | — | 2025-11 | — |
| 77 | Kimi K2 Thinking (Turbo) OPEN | Moonshot | 145.8 | — | 0.842 | 2025-11 | — |
| 78 | o4-mini | OpenAI | 145.7 | — | 0.796 (high) | 2025-04 | $1.10 / $4.40 |
| 79 | GPT-5 mini | OpenAI | 145.5 | 0.647 (medium) | 0.750 (high) | 2025-08 | $0.25 / $2.00 |
| 80 | Gemini 2.5 Pro (Jun 2025) | Google DeepMind | 145.3 | 0.576 | 0.853 | 2025-06 | — |
| 81 | Gemini 2.5 Pro (Jun 2025, Preview 06 05) | Google DeepMind | 145.3 | — | 0.848 | 2025-06 | — |
| 82 | Gemini 3.5 Flash-Lite | Google DeepMind | 145.1 | — | 0.833 (high) | 2026-07 | $0.30 / $2.50 |
| 83 | DeepSeek-V3.2-Exp OPEN | DeepSeek | 145.0 | — | — | 2025-09 | — |
| 84 | Qwen3.7 Flash | Alibaba | 144.6 | — | 0.823 | 2026-07 | — |
| 85 | Gemini 3.1 Flash-Lite | 144.5 | — | 0.818 (high) | 2026-03 | — / $1.50 | |
| 86 | Grok 4 Fast | xAI | 144.2 | — | — | 2025-09 | — |
| 87 | Gemini 2.5 Pro (Mar 2025, Exp) | Google DeepMind | 144.2 | — | 0.838 | 2025-03 | — |
| 88 | Gemini 2.5 Pro (Mar 2025, Preview) | Google DeepMind | 144.2 | — | — | 2025-03 | — |
| 89 | Claude Opus 4.1 | Anthropic | 144.1 | 0.733 | 0.773 (16k) | 2025-08 | $15.00 / $75.00 stale |
| 90 | Qwen 3.5 Flash (hosted 35B-A3B) | Alibaba | 144.0 | — | 0.823 | 2026-02 | — |
| 91 | Qwen3-235B-A22B-Thinking (Jul 2025) OPEN | Alibaba | 143.9 | — | 0.801 | 2025-07 | — |
| 92 | Qwen 3.6 35B-A3B OPEN | Alibaba | 143.9 | — | 0.848 (none) | 2026-04 | — |
| 93 | GLM-4.7 OPEN | Z.ai (Zhipu AI) | 143.5 | — | 0.833 | 2025-12 | — |
| 94 | Qwen 3.6 Flash | Alibaba | 143.3 | — | 0.833 | 2026-04 | — |
| 95 | Gemini 2.5 Flash (Sep 2025) | Google DeepMind | 143.0 | — | — | 2025-09 | — |
| 96 | Claude Opus 4 | Anthropic | 142.7 | 0.707 | 0.763 (16k) | 2025-05 | $15.00 / $75.00 stale |
| 97 | Gemma 4 31B IT OPEN | Google DeepMind | 142.7 | — | 0.758 (minimal) | 2026-04 | — |
| 98 | Qwen3.5-35B-A3B OPEN | Alibaba | 142.5 | — | 0.835 | 2026-02 | — |
| 99 | GPT-5.5 Instant | OpenAI | 142.5 | — | 0.825 | 2026-05 | — |
| 100 | Gemini 2.5 Pro (May 2025) | Google DeepMind | 142.5 | — | 0.667 | 2025-05 | — |
| 101 | Qwen3-Max | Alibaba | 142.4 | — | 0.726 | 2025-09 | — |
| 102 | Claude Haiku 4.5 | Anthropic | 142.4 | — | 0.712 (32k) | 2025-10 | $1.00 / $5.00 stale |
| 103 | o1 | OpenAI | 141.9 | — | 0.768 (high) | 2024-12 | $15.00 / $60.00 |
| 104 | Gemma 4 26B A4B OPEN | Google DeepMind | 141.9 | — | — | 2026-04 | — |
| 105 | Gemma 4 26B A4B (It) OPEN | Google DeepMind | 141.9 | — | 0.732 (minimal) | 2026-04 | — |
| 106 | Claude Sonnet 4 | Anthropic | 141.7 | — | 0.783 (32k) | 2025-05 | $3.00 / $15.00 stale |
| 107 | Gemini 2.5 Flash (May 2025) | Google DeepMind | 141.5 | — | — | 2025-05 | — |
| 108 | DeepSeek-R1 (May 2025) OPEN | DeepSeek | 141.3 | — | 0.763 | 2025-05 | — |
| 109 | Mistral Medium 3.5 OPEN | Mistral AI | 141.3 | — | — | 2026-04 | — |
| 110 | Claude 3.7 Sonnet | Anthropic | 141.2 | 0.610 | 0.785 (64k) | 2025-02 | — |
| 111 | GLM-4.6 OPEN | Z.ai (Zhipu AI) | 140.8 | — | — | 2025-09 | — |
| 112 | Gemini 2.5 Flash (Jun 2025) | Google DeepMind | 140.5 | — | — | 2025-06 | — / $2.50 |
| 113 | o3-mini | OpenAI | 140.3 | — | 0.770 (high) | 2025-01 | $1.10 / $4.40 |
| 114 | Grok-3 mini | xAI | 140.3 | — | — | 2025-06 | — |
| 115 | Grok-3 mini (Beta) | xAI | 140.3 | — | 0.763 (low) | 2025-04 | — |
| 116 | Kimi K2 (Jul 2025, 0711 Preview) OPEN | Moonshot | 140.1 | — | — | 2025-07 | — |
| 117 | Kimi K2 (Jul 2025, Instruct) OPEN | Moonshot | 140.1 | — | — | 2025-07 | — |
| 118 | gpt-oss-120b OPEN | OpenAI | 140.1 | — | 0.758 (high-openai) | 2025-08 | — |
| 119 | Gemini 2.5 Flash (Apr 2025) | Google DeepMind | 140.0 | — | — | 2025-04 | — |
| 120 | DeepSeek-V3.1 OPEN | DeepSeek | 139.9 | — | — | 2025-08 | — |
| 121 | Qwen3-30B-A3B-Thinking (Jul 2025) OPEN | Alibaba | 139.6 | — | 0.701 | 2025-07 | — |
| 122 | Qwen3.5-9B OPEN | Alibaba | 139.4 | — | 0.790 | 2026-02 | — |
| 123 | GPT-5 nano | OpenAI | 139.4 | — | 0.694 (high) | 2025-08 | $0.05 / $0.40 |
| 124 | Qwen3-235B-A22B OPEN | Alibaba | 139.3 | — | 0.707 | 2025-04 | — |
| 125 | DeepSeek-R1 OPEN | DeepSeek | 139.0 | — | 0.692 | 2025-01 | — |
| 126 | Qwen3-235B-A22B-Instruct (Jul 2025) OPEN | Alibaba | 138.9 | — | — | 2025-07 | — |
| 127 | Qwen3-32B OPEN | Alibaba | 138.5 | — | 0.657 | 2025-04 | — |
| 128 | Grok 3 | xAI | 138.3 | — | — | 2025-04 | — |
| 129 | Grok 3 (Beta) | xAI | 138.3 | — | 0.676 | 2025-04 | — |
| 130 | Qwen3-14B OPEN | Alibaba | 138.2 | — | 0.638 | 2025-04 | — |
| 131 | gpt-oss-20b OPEN | OpenAI | 137.8 | — | 0.608 (medium) | 2025-08 | — |
| 132 | QwQ-32B OPEN | Alibaba | 137.6 | — | 0.653 | 2025-03 | — |
| 133 | DeepSeek-R1-Distill-Qwen-32B OPEN | DeepSeek | 137.4 | — | 0.641 | 2025-01 | — |
| 134 | Qwen3-30B-A3B-Instruct (Jul 2025) OPEN | Alibaba | 137.4 | — | 0.556 | 2025-07 | — |
| 135 | GPT-4.1 | OpenAI | 136.8 | 0.485 | 0.669 | 2025-04 | $2.00 / $8.00 |
| 136 | GPT-4.5 | OpenAI | 136.8 | — | 0.687 | 2025-02 | — |
| 137 | Qwen3-30B-A3B OPEN | Alibaba | 136.2 | — | 0.617 | 2025-04 | — |
| 138 | Qwen3-8B OPEN | Alibaba | 136.2 | — | 0.568 | 2025-04 | — |
| 139 | DeepSeek-V3 (Mar 2025) OPEN | DeepSeek | 135.9 | — | 0.676 | 2025-03 | — |
| 140 | o1-mini | OpenAI | 135.8 | — | 0.624 (high) | 2024-09 | $1.10 / $4.40 stale |
| 141 | DeepSeek-R1-Distill-Qwen-14B OPEN | DeepSeek | 135.4 | — | 0.447 | 2025-01 | — |
| 142 | Gemini 2.0 Flash Thinking (Jan 2025) | Google DeepMind | 135.4 | — | 0.571 | 2025-01 | — |
| 143 | Gemini 2.0 Pro | Google DeepMind | 135.1 | — | 0.657 | 2025-02 | — |
| 144 | GPT-4.1 mini | OpenAI | 135.0 | — | 0.658 | 2025-04 | $0.40 / $1.60 |
| 145 | o1-preview | OpenAI | 134.8 | — | 0.503 | 2024-09 | — |
| 146 | Gemini 2.0 Flash (Dec 2024) | Google DeepMind | 134.7 | — | — | 2024-12 | — |
| 147 | Gemini 2.0 Flash (Dec 2024, 11 Dec 2024) | Google DeepMind | 134.7 | — | — | 2024-12 | — |
| 148 | Gemini 2.0 Flash (Feb 2025) (gemini-2.0-flash-001) | Google DeepMind | 134.7 | — | 0.641 | 2025-02 | — |
| 149 | Gemini 2.0 Flash (Feb 2025) (gemini-2.0-flash-02-05) | Google DeepMind | 134.7 | — | — | 2025-02 | — |
| 150 | Mistral Medium 3 | Mistral AI | 134.1 | — | 0.595 | 2025-05 | — |
| 151 | Gemini 2.5 Flash-Lite (Jun 2025) | Google DeepMind | 133.9 | — | — | 2025-06 | — |
| 152 | Gemini 2.5 Flash-Lite (Jun 2025, Thinking) | Google DeepMind | 133.9 | — | — | 2025-06 | — |
| 153 | Claude 3.5 Sonnet (October 2024) | Anthropic | 133.6 | — | 0.553 | 2024-10 | — |
| 154 | Magistral Small 1.0 OPEN | Mistral AI | 133.2 | — | 0.561 | 2025-06 | — |
| 155 | Qwen2.5-Max (25 Jan 2025) | Alibaba | 132.5 | — | 0.561 | 2025-01 | — |
| 156 | Qwen2.5-Max | Alibaba | 132.5 | — | — | 2025-01 | — |
| 157 | DeepSeek-V3 OPEN | DeepSeek | 132.3 | — | 0.565 | 2024-12 | — |
| 158 | DeepSeek-V3 (Base) OPEN | DeepSeek | 132.3 | — | — | 2024-12 | — |
| 159 | Llama 4 Maverick OPEN | Meta AI | 132.2 | — | — | 2025-04 | — |
| 160 | Llama 4 Maverick (FP8) OPEN | Meta AI | 132.2 | — | 0.670 | 2025-04 | — |
| 161 | Mistral Small 3.2 (mistral-small-3.2-2506) OPEN | Mistral AI | 131.7 | — | 0.491 | 2025-06 | — |
| 162 | Mistral Small 3.2 (mistral-small-2506) OPEN | Mistral AI | 131.7 | — | — | 2025-06 | — |
| 163 | Gemini 1.5 Pro (Sept 2024) | Google DeepMind | 131.7 | — | 0.572 | 2024-09 | — |
| 164 | Magistral Small 1.2 OPEN | Mistral AI | 131.4 | — | 0.476 | 2025-09 | — |
| 165 | Grok-2 (Dec 2024) | xAI | 130.5 | — | 0.538 | 2024-12 | — |
| 166 | Grok-2 (Dec 2024, Vision) | xAI | 130.5 | — | — | 2024-12 | — |
| 167 | Phi-4 OPEN | Microsoft Research | 130.4 | — | 0.561 | 2024-12 | — |
| 168 | Phi-4 (phi4:14b q8 0) OPEN | Microsoft Research | 130.4 | — | — | 2024-12 | — |
| 169 | Gemma 3 27B OPEN | Google DeepMind | 130.0 | — | 0.477 | 2025-03 | — |
| 170 | Claude 3.5 Sonnet | Anthropic | 130.0 | — | 0.540 | 2024-06 | — |
| 171 | Llama 4 Scout OPEN | Meta AI | 129.6 | — | 0.518 | 2025-04 | — |
| 172 | GPT-4.1 nano | OpenAI | 129.6 | — | 0.489 | 2025-04 | $0.10 / $0.40 |
| 173 | Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) | Google DeepMind | 129.4 | — | 0.473 | 2024-09 | — |
| 174 | Gemini 1.5 Flash (Sep 2024, Exp 0827) | Google DeepMind | 129.4 | — | — | 2024-09 | — |
| 175 | Qwen2.5-72B OPEN | Alibaba | 129.0 | — | — | 2024-09 | — |
| 176 | Qwen2.5-72B (Instruct) OPEN | Alibaba | 129.0 | — | 0.491 | 2024-09 | — |
| 177 | Qwen2.5-72B (Vl Instruct) OPEN | Alibaba | 129.0 | — | — | 2024-09 | — |
| 178 | GPT-4o (May 2024) | OpenAI | 129.0 | — | 0.489 | 2024-05 | $5.00 / $15.00 |
| 179 | GPT-4o (Nov 2024, Chatgpt) | OpenAI | 128.8 | — | — | 2024-11 | — |
| 180 | GPT-4o (Nov 2024) | OpenAI | 128.8 | 0.310 | 0.479 | 2024-11 | — |
| 181 | GPT-4o (Aug 2024) | OpenAI | 128.8 | — | 0.492 | 2024-08 | — |
| 182 | Llama 3.1-405B OPEN | Meta AI | 128.8 | — | — | 2024-07 | — |
| 183 | Llama 3.1-405B (Instruct) OPEN | Meta AI | 128.8 | — | 0.509 | 2024-07 | — |
| 184 | Llama 3.1-405B (Instruct q4 K) OPEN | Meta AI | 128.8 | — | — | 2024-07 | — |
| 185 | Qwen2.5-32B OPEN | Alibaba | 128.5 | — | 0.461 | 2024-09 | — |
| 186 | Qwen2.5-32B (Coder Q8 0 Gguf) OPEN | Alibaba | 128.5 | — | — | 2024-09 | — |
| 187 | Mistral Large 2 (Nov 2024) OPEN | Mistral AI | 128.5 | — | 0.513 | 2024-11 | — |
| 188 | Mistral Large 2 (Nov 2024, Instruct) OPEN | Mistral AI | 128.5 | — | — | 2024-11 | — |
| 189 | Mistral Large 2 (Jul 2024) OPEN | Mistral AI | 127.5 | — | 0.490 | 2024-07 | — |
| 190 | Mistral Large 2 (Jul 2024, Instruct) OPEN | Mistral AI | 127.5 | — | — | 2024-07 | — |
| 191 | Mistral Small 3.1 (mistral-small-3.1-2503) OPEN | Mistral AI | 127.5 | — | 0.419 | 2025-03 | — |
| 192 | Mistral Small 3.1 (mistral-small-2503) OPEN | Mistral AI | 127.5 | — | 0.475 | 2025-03 | — |
| 193 | Llama 3.3 70B OPEN | Meta AI | 127.3 | — | 0.474 | 2024-12 | — |
| 194 | GPT-4 Turbo (Apr 2024) | OpenAI | 127.2 | — | 0.466 | 2024-04 | $10.00 / $30.00 |
| 195 | Claude 3.5 Haiku | Anthropic | 127.2 | — | 0.381 | 2024-10 | — |
| 196 | Mistral Small 3 (mistral-small-3-2501) OPEN | Mistral AI | 127.1 | — | 0.473 | 2025-01 | — |
| 197 | Mistral Small 3 (mistral-small-2501) OPEN | Mistral AI | 127.1 | — | 0.453 | 2025-01 | — |
| 198 | Claude 3 Opus | Anthropic | 126.9 | — | 0.472 | 2024-02 | — |
| 199 | Gemini 1.5 Pro (May 2024) | Google DeepMind | 126.9 | — | 0.459 | 2024-05 | — |
| 200 | GPT-4o mini | OpenAI | 126.6 | — | 0.377 | 2024-07 | $0.15 / $0.60 |
| 201 | GPT-4 Turbo (Jan 2024, 0125 Preview) | OpenAI | 126.5 | — | 0.423 | 2024-01 | $10.00 / $30.00 stale |
| 202 | GPT-4 Turbo (Jan 2024, 1106 Preview) | OpenAI | 126.5 | — | 0.424 | 2023-11 | $10.00 / $30.00 stale |
| 203 | GPT-4 Turbo (Jan 2024) | OpenAI | 126.5 | — | — | 2024-01 | — |
| 204 | Llama 3.1-70B OPEN | Meta AI | 125.9 | — | 0.442 | 2024-07 | — |
| 205 | GPT-4 (Mar 2023, 32k) | OpenAI | 125.9 | — | — | 2023-03 | — |
| 206 | GPT-4 (Mar 2023) | OpenAI | 125.9 | — | 0.357 | 2023-03 | $30.00 / $60.00 stale |
| 207 | Llama 3.2 90B OPEN | Meta AI | 125.5 | — | 0.410 | 2024-09 | — |
| 208 | Qwen2-72B OPEN | Alibaba | 125.3 | — | 0.408 | 2024-06 | — |
| 209 | DeepSeek-V2 (MoE-236B, May 2024) OPEN | DeepSeek | 124.8 | — | — | 2024-05 | — |
| 210 | Amazon Nova Pro | Amazon | 123.8 | — | — | 2024-12 | — |
| 211 | Gemma 3 12B OPEN | Google DeepMind | 123.5 | — | 0.395 | 2025-03 | — |
| 212 | GPT-4 (Jun 2023, 32k) | OpenAI | 123.1 | — | — | 2023-06 | — |
| 213 | GPT-4 (Jun 2023) | OpenAI | 123.1 | — | 0.307 | 2023-06 | $30.00 / $60.00 |
| 214 | Llama 3-70B OPEN | Meta AI | 122.9 | — | — | 2024-04 | — |
| 215 | Llama 3-70B (Instruct) OPEN | Meta AI | 122.9 | — | 0.406 | 2024-04 | — |
| 216 | Gemini 1.5 Flash (May 2024) (gemini-1.5-flash-001) | Google DeepMind | 122.6 | — | 0.404 | 2024-05 | — |
| 217 | Gemini 1.5 Flash (May 2024) (gemini-1.5-flash-0514) | Google DeepMind | 122.6 | — | — | 2024-05 | — |
| 218 | Gemma 2 27B OPEN | Google DeepMind | 122.0 | — | — | 2024-06 | — |
| 219 | Gemma 2 27B (It) OPEN | Google DeepMind | 122.0 | — | 0.365 | 2024-06 | — |
| 220 | Gemma 2 27B (Instruct q8 0) OPEN | Google DeepMind | 122.0 | — | — | 2024-06 | — |
| 221 | Mixtral 8x22B (Instruct v0.1) OPEN | Mistral AI | 122.0 | — | — | 2024-04 | — |
| 222 | Mixtral 8x22B (v0.1) OPEN | Mistral AI | 122.0 | — | — | 2024-04 | — |
| 223 | Mixtral 8x22B (Open) OPEN | Mistral AI | 122.0 | — | 0.341 | 2024-04 | — |
| 224 | Mistral Large | Mistral AI | 122.0 | — | 0.388 | 2024-02 | — |
| 225 | phi-3-small 7.4B OPEN | Microsoft | 121.8 | — | — | 2024-04 | — |
| 226 | phi-3-medium 14B OPEN | Microsoft | 121.2 | — | 0.276 | 2024-04 | — |
| 227 | Claude 3 Sonnet | Anthropic | 120.7 | — | 0.406 | 2024-02 | — |
| 228 | Claude Instant (1.1) | Anthropic | 120.2 | — | — | 2023-08 | — |
| 229 | Claude Instant (1.2) | Anthropic | 120.2 | — | — | 2023-08 | — |
| 230 | Claude 2 | Anthropic | 120.1 | — | 0.347 | 2023-07 | — |
| 231 | Gemma 2 9B OPEN | Google DeepMind | 119.8 | — | — | 2024-06 | — |
| 232 | Gemma 2 9B (It) OPEN | Google DeepMind | 119.8 | — | 0.275 | 2024-06 | — |
| 233 | Qwen2.5-Coder-32B OPEN | Alibaba | 119.4 | — | — | 2024-09 | — |
| 234 | Command R+ OPEN | Cohere | 119.2 | — | — | 2024-08 | — |
| 235 | Claude 2.1 | Anthropic | 119.2 | — | 0.330 | 2023-11 | — |
| 236 | Mistral NeMo (Base) OPEN | Mistral AI | 118.6 | — | — | 2024-07 | — |
| 237 | Mistral NeMo (Instruct) OPEN | Mistral AI | 118.6 | — | — | 2024-07 | — |
| 238 | Mistral NeMo (Open) OPEN | Mistral AI | 118.6 | — | 0.299 | 2024-07 | — |
| 239 | GPT-3.5 Turbo (Nov 2023) | OpenAI | 118.5 | — | 0.280 | 2023-11 | $1.00 / $2.00 |
| 240 | Qwen2.5-7B OPEN | Alibaba | 118.4 | — | 0.355 | 2024-09 | — |
| 241 | Mixtral 8x7B (Instruct v0.1) OPEN | Mistral AI | 118.4 | — | 0.306 | 2023-12 | — |
| 242 | Mixtral 8x7B (v0.1) OPEN | Mistral AI | 118.4 | — | — | 2023-12 | — |
| 243 | Mixtral 8x7B (Open) OPEN | Mistral AI | 118.4 | — | 0.298 | 2023-12 | — |
| 244 | Claude 3 Haiku | Anthropic | 118.3 | — | 0.363 | 2024-03 | — |
| 245 | Ministral 3B | Mistral AI | 118.1 | — | — | 2024-10 | — |
| 246 | Ministral 3B (16 Oct 2024) | Mistral AI | 118.1 | — | 0.253 | 2024-10 | — |
| 247 | Yi-34B OPEN | 01.AI | 117.3 | — | — | 2023-11 | — |
| 248 | Yi-34B (Chat) OPEN | 01.AI | 117.3 | — | 0.147 | 2023-11 | — |
| 249 | phi-3-mini 3.8B (4k) OPEN | Microsoft | 117.2 | — | — | 2024-04 | — |
| 250 | phi-3-mini 3.8B (128k) OPEN | Microsoft | 117.2 | — | — | 2024-04 | — |
| 251 | Stable Beluga 2 OPEN | Stability AI | 117.0 | — | — | 2023-07 | — |
| 252 | Gemini 1.0 Pro | Google DeepMind | 117.0 | — | 0.340 | 2023-12 | — |
| 253 | Llama 3.1-8B OPEN | Meta AI | 116.5 | — | 0.270 | 2024-07 | — |
| 254 | Llama 3-8B OPEN | Meta AI | 116.3 | — | — | 2024-04 | — |
| 255 | Llama 3-8B (Instruct) OPEN | Meta AI | 116.3 | — | 0.261 | 2024-04 | — |
| 256 | Qwen2.5-Coder-14B | — | 116.3 | — | — | 2024-09 | — |
| 257 | Gemma 3 4B OPEN | Google DeepMind | 116.0 | — | 0.232 | 2025-03 | — |
| 258 | GPT-3.5 Turbo (Jan 2024) | OpenAI | 115.6 | — | 0.272 | 2024-01 | $0.50 / $1.50 |
| 259 | PaLM 2-L | — | 114.9 | — | — | 2023-05 | — |
| 260 | Llama 2-70B (Chat) OPEN | Meta AI | 113.6 | — | 0.263 (hf) | 2023-07 | — |
| 261 | Llama 2-70B (Hf) OPEN | Meta AI | 113.6 | — | — | 2023-07 | — |
| 262 | GPT-3.5 Turbo (Jun 2023, 16k) | OpenAI | 113.2 | — | — | 2023-06 | — |
| 263 | GPT-3.5 Turbo (Jun 2023) | OpenAI | 113.2 | — | — | 2023-06 | $1.50 / $2.00 stale |
| 264 | Qwen2.5-Coder (7B) OPEN | Alibaba | 113.0 | — | — | 2024-09 | — |
| 265 | Qwen2.5-Coder (7B, Instruct) OPEN | Alibaba | 113.0 | — | — | 2024-09 | — |
| 266 | Qwen-14B OPEN | Alibaba | 112.8 | — | — | 2023-09 | — |
| 267 | Qwen-14B (Chat) OPEN | Alibaba | 112.8 | — | — | 2023-09 | — |
| 268 | Mistral 7B v0.1 (Instruct) OPEN | Mistral AI | 112.0 | — | — | 2023-09 | — |
| 269 | Mistral 7B v0.1 OPEN | Mistral AI | 112.0 | — | — | 2023-09 | — |
| 270 | Falcon-180B OPEN | Technology Innovation Institute | 111.9 | — | — | 2023-09 | — |
| 271 | internlm-20b | — | 111.9 | — | — | 2023-09 | — |
| 272 | Gemma 7B OPEN | Google DeepMind | 111.8 | — | — | 2024-02 | — |
| 273 | DeepSeek LLM 67B (Base) OPEN | DeepSeek | 110.6 | — | — | 2023-11 | — |
| 274 | DeepSeek LLM 67B (Chat) OPEN | DeepSeek | 110.6 | — | 0.246 | 2023-11 | — |
| 275 | LLaMA-65B OPEN | Meta AI | 109.9 | — | — | 2023-02 | — |
| 276 | Falcon 2 11B OPEN | Technology Innovation Institute | 109.3 | — | — | 2024-05 | — |
| 277 | Mistral 7B v0.3 (Instruct) OPEN | Mistral AI | 108.8 | — | 0.152 | 2024-05 | — |
| 278 | Mistral 7B v0.3 OPEN | Mistral AI | 108.8 | — | — | 2024-05 | — |
| 279 | Mistral 7B v0.3 (Open) OPEN | Mistral AI | 108.8 | — | 0.132 | 2023-09 | — |
| 280 | DeepSeek-Coder-V2-Lite-Base | — | 108.6 | — | — | 2024-06 | — |
| 281 | PaLM 2-M | — | 108.0 | — | — | 2023-05 | — |
| 282 | Phi-2 OPEN | Microsoft | 107.7 | — | — | 2023-12 | — |
| 283 | Qwen2.5-Coder-3B | — | 107.5 | — | — | 2024-09 | — |
| 284 | Nemotron-4 15B | NVIDIA | 107.5 | — | — | 2024-02 | — |
| 285 | Yi-9B | — | 107.3 | — | — | 2024-03 | — |
| 286 | LLaMA-33B OPEN | Meta AI | 107.1 | — | — | 2023-02 | — |
| 287 | Qwen-7B OPEN | Alibaba | 106.5 | — | — | 2023-09 | — |
| 288 | Llama 2-13B OPEN | Meta AI | 105.9 | — | — | 2023-07 | — |
| 289 | Llama 2-13B (Chat) OPEN | Meta AI | 105.9 | — | — | 2023-07 | — |
| 290 | PaLM 2-S | — | 105.9 | — | — | 2023-05 | — |
| 291 | Llama 2-34B | Meta AI | 104.9 | — | — | 2023-07 | — |
| 292 | StarCoder 2 15B OPEN | Hugging Face | 104.7 | — | — | 2024-02 | — |
| 293 | Yi 6B OPEN | 01.AI | 104.5 | — | — | 2023-11 | — |
| 294 | Yi 6B (Chat) OPEN | 01.AI | 104.5 | — | — | 2023-11 | — |
| 295 | Falcon-40B OPEN | Technology Innovation Institute | 104.1 | — | — | 2023-05 | — |
| 296 | Falcon-40B (Instruct) OPEN | Technology Innovation Institute | 104.1 | — | — | 2023-05 | — |
| 297 | Baichuan2-13B OPEN | Baichuan | 102.9 | — | — | 2023-09 | — |
| 298 | Qwen2.5-Coder (1.5B) OPEN | Alibaba | 102.7 | — | — | 2024-09 | — |
| 299 | internlm-7b | — | 102.5 | — | — | 2023-07 | — |
| 300 | Llama 3.2 1B OPEN | Meta AI | 102.4 | — | 0.239 | 2024-09 | — |
| 301 | INTELLECT-1 | Prime Intellect | 100.5 | — | — | 2024-11 | — |
| 302 | MPT-30B OPEN | MosaicML | 100.3 | — | — | 2023-06 | — |
| 303 | MPT-30B (Instruct) OPEN | MosaicML | 100.3 | — | — | 2023-06 | — |
| 304 | LLaMA-13B OPEN | Meta AI | 100.2 | — | — | 2023-02 | — |
| 305 | Llama 2-7B OPEN | Meta AI | 98.7 | — | — | 2023-07 | — |
| 306 | Llama 2-7B (Chat) OPEN | Meta AI | 98.7 | — | — | 2023-07 | — |
| 307 | chatglm2-6b | — | 98.5 | — | — | 2023-06 | — |
| 308 | LLaMA-7B OPEN | Meta AI | 96.2 | — | — | 2023-02 | — |
| 309 | Baichuan 2-7B OPEN | Baichuan | 95.9 | — | — | 2023-09 | — |
| 310 | DeepSeek Coder 33B (Base) OPEN | DeepSeek | 95.9 | — | — | 2023-11 | — |
| 311 | DeepSeek Coder 33B (Instruct) OPEN | DeepSeek | 95.9 | — | — | 2023-11 | — |
| 312 | Falcon-7B OPEN | Technology Innovation Institute | 94.6 | — | — | 2023-04 | — |
| 313 | CodeQwen1.5-7B | — | 94.4 | — | — | 2024-04 | — |
| 314 | vicuna-13b-v1.1 | — | 94.2 | — | — | 2023-04 | — |
| 315 | MPT-7B OPEN | MosaicML | 94.1 | — | — | 2023-05 | — |
| 316 | MPT-7B (Instruct) OPEN | MosaicML | 94.1 | — | — | 2023-05 | — |
| 317 | Gemma 2B OPEN | Google DeepMind | 93.7 | — | — | 2024-02 | — |
| 318 | StarCoder 2 7B OPEN | Hugging Face | 93.1 | — | — | 2024-02 | — |
| 319 | XGen-7B OPEN | Salesforce | 92.9 | — | — | 2023-06 | — |
| 320 | Qwen-1_8B | — | 92.4 | — | — | 2023-11 | — |
| 321 | open_llama_7b | — | 91.1 | — | — | 2023-06 | — |
| 322 | Phi-1.5 OPEN | Microsoft | 91.0 | — | — | 2023-09 | — |
| 323 | Baichuan1-7B OPEN | Baichuan | 89.9 | — | — | 2023-06 | — |
| 324 | RedPajama-INCITE-7B-Base | — | 89.9 | — | — | 2023-05 | — |
| 325 | Dolly 2.0-12b OPEN | Databricks | 89.1 | — | — | 2023-04 | — |
| 326 | DeepSeek Coder 6.7B (Base) OPEN | DeepSeek | 89.0 | — | — | 2023-11 | — |
| 327 | DeepSeek Coder 6.7B (Instruct) OPEN | DeepSeek | 89.0 | — | — | 2023-11 | — |
| 328 | DeepSeek Coder 6.7B (Base v1.5) OPEN | DeepSeek | 89.0 | — | — | 2023-11 | — |
| 329 | StarCoder 2 3B OPEN | Hugging Face | 88.2 | — | — | 2024-02 | — |
| 330 | Qwen2.5-Coder-0.5B | — | 87.6 | — | — | 2024-09 | — |
| 331 | Cerebras-GPT-13B OPEN | Cerebras Systems | 82.6 | — | — | 2023-03 | — |
| 332 | DeepSeek Coder 1.3B (Base) OPEN | DeepSeek | 62.5 | — | — | 2023-11 | — |
| 333 | DeepSeek Coder 1.3B (Instruct) OPEN | DeepSeek | 62.5 | — | — | 2023-11 | — |
| 334 | stablelm-tuned-alpha-7b | — | 54.6 | — | — | 2023-04 | — |
Scroll to see more →
| Rank | Model | Provider | Overall | Coding | Reasoning | Released | Price |
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 4.7 | Anthropic | 156.3 | 0.835 (max) | 0.902 (xhigh) | 2026-04 | $5.00 / $25.00 stale |
| 2 | GPT-5.5 | OpenAI | 159.1 | 0.806 (xhigh-pre-release) | 0.940 (xhigh-pre-release) | 2026-04 | $5.00 / $30.00 |
| 3 | Gemini 3.5 Flash | Google DeepMind | 154.7 | 0.793 (high) | 0.928 (high) | 2026-05 | $1.50 / $9.00 |
| 4 | GLM-5.2 OPEN | Z.ai (Zhipu AI) | 151.9 | 0.787 (max) | 0.919 (max) | 2026-06 | — |
| 5 | DeepSeek-V4-Pro OPEN | DeepSeek | 149.1 | 0.776 (max) | 0.909 (high) | 2026-04 | — |
| 6 | Qwen3.7-Max | Alibaba | 153.7 | 0.773 | 0.909 | 2026-05 | — |
| 7 | Claude Opus 4.6 | Anthropic | 155.3 | 0.772 | 0.905 (32k) | 2026-02 | $5.00 / $25.00 stale |
| 8 | GPT-5.4 | OpenAI | 156.9 | 0.769 (high) | 0.933 (xhigh) | 2026-03 | $2.50 / $15.00 |
| 9 | Qwen 3.6 Max (Preview) | Alibaba | 149.3 | 0.767 | 0.874 | 2026-04 | — |
| 10 | Kimi K2.6 OPEN | Moonshot | 151.0 | 0.767 | 0.908 | 2026-04 | — |
| 11 | Claude Opus 4.5 | Anthropic | 150.1 | 0.767 | 0.860 (32k) | 2025-11 | $5.00 / $25.00 stale |
| 12 | Gemini 3.1 Pro | Google DeepMind | 155.0 | 0.756 (customtools) | 0.944 (high) | 2026-02 | — |
| 13 | Gemini 3 Flash | Google DeepMind | 151.8 | 0.754 | 0.894 (high) | 2025-12 | — / $3.00 |
| 14 | Claude Sonnet 4.6 | Anthropic | 152.2 | 0.752 | 0.874 (32k) | 2026-02 | $3.00 / $15.00 stale |
| 15 | GPT-5.3 Codex | OpenAI | 156.6 | 0.748 (high) | — | 2026-02 | — |
| 16 | GLM-5.1 OPEN | Z.ai (Zhipu AI) | 149.7 | 0.742 | 0.899 | 2026-04 | — |
| 17 | Kimi K2.5 OPEN | Moonshot | 148.0 | 0.738 | 0.876 (fireworks) | 2026-01 | — |
| 18 | GPT-5.2 | OpenAI | 153.5 | 0.738 (high) | 0.914 (xhigh) | 2025-12 | $1.75 / $14.00 |
| 19 | GPT-5 (07 Aug 2025) | OpenAI | 150.0 | 0.736 (high) | 0.862 (high) | 2025-08 | — |
| 20 | Claude Opus 4.1 | Anthropic | 144.1 | 0.733 | 0.773 (16k) | 2025-08 | $15.00 / $75.00 stale |
| 21 | Gemini 3 Pro | Google DeepMind | 153.0 | 0.729 | 0.926 | 2025-11 | — |
| 22 | GLM-5 OPEN | Z.ai (Zhipu AI) | 145.8 | 0.721 | 0.878 | 2026-02 | — |
| 23 | Claude Sonnet 4.5 | Anthropic | 146.8 | 0.713 | 0.823 (59k) | 2025-09 | $3.00 / $15.00 stale |
| 24 | Claude Opus 4 | Anthropic | 142.7 | 0.707 | 0.763 (16k) | 2025-05 | $15.00 / $75.00 stale |
| 25 | GPT-5.1 | OpenAI | 149.6 | 0.669 (high) | 0.876 (high) | 2025-11 | $1.25 / $10.00 |
| 26 | GPT-5 mini | OpenAI | 145.5 | 0.647 (medium) | 0.750 (high) | 2025-08 | $0.25 / $2.00 |
| 27 | o3 | OpenAI | 146.9 | 0.623 (medium) | 0.818 (high) | 2025-04 | $2.00 / $8.00 |
| 28 | Claude 3.7 Sonnet | Anthropic | 141.2 | 0.610 | 0.785 (64k) | 2025-02 | — |
| 29 | Qwen 3.6 Plus | Alibaba | 147.7 | 0.579 | 0.884 | 2026-03 | — |
| 30 | Gemini 2.5 Pro (Jun 2025) | Google DeepMind | 145.3 | 0.576 | 0.853 | 2025-06 | — |
| 31 | GPT-4.1 | OpenAI | 136.8 | 0.485 | 0.669 | 2025-04 | $2.00 / $8.00 |
| 32 | GPT-4o (Nov 2024) | OpenAI | 128.8 | 0.310 | 0.479 | 2024-11 | — |
Scroll to see more →
| Rank | Model | Provider | Overall | Coding | Reasoning | Released | Price |
|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | 166.3 | — | 0.958 (max) | 2026-09 | $10.00 / $50.00 |
| 2 | Gemini 3.8 Flash | Google DeepMind | 156.5 | — | 0.954 (high) | 2026-09 | — |
| 3 | Gemini 3.7 Flash | Google DeepMind | 157.4 | — | 0.948 (high) | 2026-08 | — |
| 4 | GPT-5.4 Pro | OpenAI | 158.9 | — | 0.946 (xhigh) | 2026-03 | $30.00 / $180.00 |
| 5 | Gemini 3.1 Pro | Google DeepMind | 155.0 | 0.756 (customtools) | 0.944 (high) | 2026-02 | — |
| 6 | Gemini 3.6 Flash | Google DeepMind | 154.3 | — | 0.941 (high) | 2026-07 | — |
| 7 | Grok 4.6 | xAI | 156.3 | — | 0.940 (high) | 2026-08 | — |
| 8 | GPT-5.5 | OpenAI | 159.1 | 0.806 (xhigh-pre-release) | 0.940 (xhigh-pre-release) | 2026-04 | $5.00 / $30.00 |
| 9 | GPT-5.5 Pro | OpenAI | 162.2 | — | 0.939 (xhigh-pre-release) | 2026-04 | $30.00 / $180.00 |
| 10 | Claude Opus 5 | Anthropic | 162.3 | — | 0.939 (max) | 2026-07 | $5.00 / $25.00 stale |
| 11 | GPT-5.6 Sol | OpenAI | 161.8 | — | 0.935 (max) | 2026-07 | $4.00 / $20.00 |
| 12 | Grok 4.5 | xAI | 153.9 | — | 0.934 (high) | 2026-07 | — |
| 13 | GPT-5.6 Terra | OpenAI | 159.1 | — | 0.933 (max) | 2026-07 | $2.00 / $12.00 |
| 14 | GPT-5.4 | OpenAI | 156.9 | 0.769 (high) | 0.933 (xhigh) | 2026-03 | $2.50 / $15.00 |
| 15 | Kimi K3 OPEN | Moonshot | 157.6 | — | 0.931 (max) | 2026-07 | — |
| 16 | Gemini 3.5 Flash | Google DeepMind | 154.7 | 0.793 (high) | 0.928 (high) | 2026-05 | $1.50 / $9.00 |
| 17 | Qwen 3.8 Max | Alibaba | 156.6 | — | 0.927 (xhigh) | 2026-08 | — |
| 18 | Gemini 3 Pro | Google DeepMind | 153.0 | 0.729 | 0.926 | 2025-11 | — |
| 19 | Qwen3.8 Max (0902) | Alibaba | 155.2 | — | 0.923 (xhigh) | 2026-09 | — |
| 20 | GLM-5.2 OPEN | Z.ai (Zhipu AI) | 151.9 | 0.787 (max) | 0.919 (max) | 2026-06 | — |
| 21 | DeepSeek V4 Pro 0813 OPEN | DeepSeek | 155.5 | — | 0.917 (max) | 2026-08 | — |
| 22 | GPT-5.6 Luna | OpenAI | 156.3 | — | 0.916 (max) | 2026-07 | $0.20 / $1.20 |
| 23 | GPT-5.2 | OpenAI | 153.5 | 0.738 (high) | 0.914 (xhigh) | 2025-12 | $1.75 / $14.00 |
| 24 | Claude Opus 4.8 | Anthropic | 158.3 | — | 0.910 (max) | 2026-05 | $5.00 / $25.00 stale |
| 25 | DeepSeek V4 Flash 0731 OPEN | DeepSeek | 154.5 | — | 0.910 (max) | 2026-07 | — |
| 26 | GLM-5.3 | Z.ai (Zhipu AI) | 155.2 | — | 0.909 (max) | 2026-08 | — |
| 27 | MiniMax-M3 OPEN | MiniMax | 146.5 | — | 0.909 | 2026-06 | — |
| 28 | Qwen3.7-Max | Alibaba | 153.7 | 0.773 | 0.909 | 2026-05 | — |
| 29 | DeepSeek-V4-Pro OPEN | DeepSeek | 149.1 | 0.776 (max) | 0.909 (high) | 2026-04 | — |
| 30 | Kimi K2.6 OPEN | Moonshot | 151.0 | 0.767 | 0.908 | 2026-04 | — |
| 31 | Claude Opus 4.6 | Anthropic | 155.3 | 0.772 | 0.905 (32k) | 2026-02 | $5.00 / $25.00 stale |
| 32 | Claude Sonnet 5 | Anthropic | 156.2 | — | 0.905 (xhigh) | 2026-06 | $2.00 / $10.00 stale |
| 33 | GLM-5.3-Flash OPEN | Z.ai (Zhipu AI) | 151.4 | — | 0.902 (max) | 2026-08 | — |
| 34 | Claude Opus 4.7 | Anthropic | 156.3 | 0.835 (max) | 0.902 (xhigh) | 2026-04 | $5.00 / $25.00 stale |
| 35 | GLM-5.1 OPEN | Z.ai (Zhipu AI) | 149.7 | 0.742 | 0.899 | 2026-04 | — |
| 36 | Muse Spark | Meta AI | 152.1 | — | 0.898 | 2026-04 | — |
| 37 | Gemini 3 Flash | Google DeepMind | 151.8 | 0.754 | 0.894 (high) | 2025-12 | — / $3.00 |
| 38 | Grok 4.20 (0309 Reasoning) | xAI | 152.0 | — | 0.893 | 2026-02 | — |
| 39 | Grok 4.3 Beta | xAI | 149.2 | — | 0.888 (high) | 2026-04 | — |
| 40 | Inkling-Small OPEN | Thinking Machines | 150.2 | — | 0.885 (xhigh) | 2026-07 | — |
| 41 | Qwen 3.6 Plus | Alibaba | 147.7 | 0.579 | 0.884 | 2026-03 | — |
| 42 | Inkling OPEN | Thinking Machines | 148.6 | — | 0.883 (xhigh) | 2026-07 | — |
| 43 | Kimi K2.7 Code OPEN | Moonshot | 150.1 | — | 0.879 | 2026-06 | — |
| 44 | Qwen3.7-Plus | Alibaba | 147.4 | — | 0.879 | 2026-06 | — |
| 45 | GLM-5 OPEN | Z.ai (Zhipu AI) | 145.8 | 0.721 | 0.878 | 2026-02 | — |
| 46 | GPT-5.1 | OpenAI | 149.6 | 0.669 (high) | 0.876 (high) | 2025-11 | $1.25 / $10.00 |
| 47 | Kimi K2.5 OPEN | Moonshot | 148.0 | 0.738 | 0.876 (fireworks) | 2026-01 | — |
| 48 | Qwen 3.6 Max (Preview) | Alibaba | 149.3 | 0.767 | 0.874 | 2026-04 | — |
| 49 | Claude Sonnet 4.6 | Anthropic | 152.2 | 0.752 | 0.874 (32k) | 2026-02 | $3.00 / $15.00 stale |
| 50 | Grok 4 | xAI | 146.4 | — | 0.870 | 2025-07 | — |
| 51 | GPT-5.4 Mini | OpenAI | 149.0 | — | 0.869 (xhigh) | 2026-03 | $0.75 / $4.50 |
| 52 | Qwen3.5 397B-A17B OPEN | Alibaba | 147.0 | — | 0.864 (none) | 2026-02 | — |
| 53 | GPT-5 (07 Aug 2025) | OpenAI | 150.0 | 0.736 (high) | 0.862 (high) | 2025-08 | — |
| 54 | Claude Opus 4.5 | Anthropic | 150.1 | 0.767 | 0.860 (32k) | 2025-11 | $5.00 / $25.00 stale |
| 55 | Qwen3.6 27B OPEN | Alibaba | 146.5 | — | 0.859 | 2026-04 | — |
| 56 | Claude Fable 5 | Anthropic | 163.3 | — | 0.859 (max) | 2026-06 | $10.00 / $50.00 stale |
| 57 | Nemotron 3 Ultra OPEN | NVIDIA | 146.3 | — | 0.854 | 2026-06 | — |
| 58 | Gemini 2.5 Pro (Jun 2025) | Google DeepMind | 145.3 | 0.576 | 0.853 | 2025-06 | — |
| 59 | Qwen 3.5 Plus (hosted 397B-A17B) | Alibaba | 146.7 | — | 0.848 | 2026-02 | — |
| 60 | Qwen 3.6 35B-A3B OPEN | Alibaba | 143.9 | — | 0.848 (none) | 2026-04 | — |
| 61 | Gemini 2.5 Pro (Jun 2025, Preview 06 05) | Google DeepMind | 145.3 | — | 0.848 | 2025-06 | — |
| 62 | Kimi K2 Thinking (Turbo) OPEN | Moonshot | 145.8 | — | 0.842 | 2025-11 | — |
| 63 | Gemini 2.5 Pro (Mar 2025, Exp) | Google DeepMind | 144.2 | — | 0.838 | 2025-03 | — |
| 64 | Qwen3.5-35B-A3B OPEN | Alibaba | 142.5 | — | 0.835 | 2026-02 | — |
| 65 | DeepSeek-V3.2 (Reasoner) OPEN | DeepSeek | 146.2 | — | 0.834 | 2025-12 | — |
| 66 | Qwen 3.6 Flash | Alibaba | 143.3 | — | 0.833 | 2026-04 | — |
| 67 | Gemini 3.5 Flash-Lite | Google DeepMind | 145.1 | — | 0.833 (high) | 2026-07 | $0.30 / $2.50 |
| 68 | GLM-4.7 OPEN | Z.ai (Zhipu AI) | 143.5 | — | 0.833 | 2025-12 | — |
| 69 | GPT-5.5 Instant | OpenAI | 142.5 | — | 0.825 | 2026-05 | — |
| 70 | Qwen3.7 Flash | Alibaba | 144.6 | — | 0.823 | 2026-07 | — |
| 71 | Qwen 3.5 Flash (hosted 35B-A3B) | Alibaba | 144.0 | — | 0.823 | 2026-02 | — |
| 72 | Claude Sonnet 4.5 | Anthropic | 146.8 | 0.713 | 0.823 (59k) | 2025-09 | $3.00 / $15.00 stale |
| 73 | o3 | OpenAI | 146.9 | 0.623 (medium) | 0.818 (high) | 2025-04 | $2.00 / $8.00 |
| 74 | Gemini 3.1 Flash-Lite | 144.5 | — | 0.818 (high) | 2026-03 | — / $1.50 | |
| 75 | Qwen3-235B-A22B-Thinking (Jul 2025) OPEN | Alibaba | 143.9 | — | 0.801 | 2025-07 | — |
| 76 | o4-mini | OpenAI | 145.7 | — | 0.796 (high) | 2025-04 | $1.10 / $4.40 |
| 77 | Qwen3.5-9B OPEN | Alibaba | 139.4 | — | 0.790 | 2026-02 | — |
| 78 | Claude 3.7 Sonnet | Anthropic | 141.2 | 0.610 | 0.785 (64k) | 2025-02 | — |
| 79 | GPT-5.4 Nano | OpenAI | 145.8 | — | 0.785 (high) | 2026-03 | $0.20 / $1.25 |
| 80 | Claude Sonnet 4 | Anthropic | 141.7 | — | 0.783 (32k) | 2025-05 | $3.00 / $15.00 stale |
| 81 | Claude Opus 4.1 | Anthropic | 144.1 | 0.733 | 0.773 (16k) | 2025-08 | $15.00 / $75.00 stale |
| 82 | o3-mini | OpenAI | 140.3 | — | 0.770 (high) | 2025-01 | $1.10 / $4.40 |
| 83 | o1 | OpenAI | 141.9 | — | 0.768 (high) | 2024-12 | $15.00 / $60.00 |
| 84 | DeepSeek-R1 (May 2025) OPEN | DeepSeek | 141.3 | — | 0.763 | 2025-05 | — |
| 85 | Grok-3 mini (Beta) | xAI | 140.3 | — | 0.763 (low) | 2025-04 | — |
| 86 | Claude Opus 4 | Anthropic | 142.7 | 0.707 | 0.763 (16k) | 2025-05 | $15.00 / $75.00 stale |
| 87 | Gemma 4 31B IT OPEN | Google DeepMind | 142.7 | — | 0.758 (minimal) | 2026-04 | — |
| 88 | gpt-oss-120b OPEN | OpenAI | 140.1 | — | 0.758 (high-openai) | 2025-08 | — |
| 89 | GPT-5 mini | OpenAI | 145.5 | 0.647 (medium) | 0.750 (high) | 2025-08 | $0.25 / $2.00 |
| 90 | Gemma 4 26B A4B (It) OPEN | Google DeepMind | 141.9 | — | 0.732 (minimal) | 2026-04 | — |
| 91 | Qwen3-Max | Alibaba | 142.4 | — | 0.726 | 2025-09 | — |
| 92 | None (seed-oss-36b-instruct) | — | — | — | 0.715 | 2025-08 | — |
| 93 | DeepSeek-V3.2 (Chat) OPEN | DeepSeek | 146.2 | — | 0.712 | 2025-12 | — |
| 94 | Claude Haiku 4.5 | Anthropic | 142.4 | — | 0.712 (32k) | 2025-10 | $1.00 / $5.00 stale |
| 95 | Qwen3-235B-A22B OPEN | Alibaba | 139.3 | — | 0.707 | 2025-04 | — |
| 96 | Qwen3-30B-A3B-Thinking (Jul 2025) OPEN | Alibaba | 139.6 | — | 0.701 | 2025-07 | — |
| 97 | GPT-5 nano | OpenAI | 139.4 | — | 0.694 (high) | 2025-08 | $0.05 / $0.40 |
| 98 | DeepSeek-R1 OPEN | DeepSeek | 139.0 | — | 0.692 | 2025-01 | — |
| 99 | GPT-4.5 | OpenAI | 136.8 | — | 0.687 | 2025-02 | — |
| 100 | DeepSeek-V3 (Mar 2025) OPEN | DeepSeek | 135.9 | — | 0.676 | 2025-03 | — |
| 101 | Grok 3 (Beta) | xAI | 138.3 | — | 0.676 | 2025-04 | — |
| 102 | Llama 4 Maverick (FP8) OPEN | Meta AI | 132.2 | — | 0.670 | 2025-04 | — |
| 103 | GPT-4.1 | OpenAI | 136.8 | 0.485 | 0.669 | 2025-04 | $2.00 / $8.00 |
| 104 | Gemini 2.5 Pro (May 2025) | Google DeepMind | 142.5 | — | 0.667 | 2025-05 | — |
| 105 | GPT-4.1 mini | OpenAI | 135.0 | — | 0.658 | 2025-04 | $0.40 / $1.60 |
| 106 | Qwen3-32B OPEN | Alibaba | 138.5 | — | 0.657 | 2025-04 | — |
| 107 | Gemini 2.0 Pro | Google DeepMind | 135.1 | — | 0.657 | 2025-02 | — |
| 108 | QWQ-Plus | Alibaba | — | — | 0.654 | 2025-04 | — |
| 109 | QwQ-32B OPEN | Alibaba | 137.6 | — | 0.653 | 2025-03 | — |
| 110 | DeepSeek-R1-Distill-Qwen-32B OPEN | DeepSeek | 137.4 | — | 0.641 | 2025-01 | — |
| 111 | Gemini 2.0 Flash (Feb 2025) (gemini-2.0-flash-001) | Google DeepMind | 134.7 | — | 0.641 | 2025-02 | — |
| 112 | Qwen3-14B OPEN | Alibaba | 138.2 | — | 0.638 | 2025-04 | — |
| 113 | o1-mini | OpenAI | 135.8 | — | 0.624 (high) | 2024-09 | $1.10 / $4.40 stale |
| 114 | Qwen3-30B-A3B OPEN | Alibaba | 136.2 | — | 0.617 | 2025-04 | — |
| 115 | gpt-oss-20b OPEN | OpenAI | 137.8 | — | 0.608 (medium) | 2025-08 | — |
| 116 | None (glm-4.7-flash) | — | — | — | 0.605 | — | — |
| 117 | Mistral Medium 3 | Mistral AI | 134.1 | — | 0.595 | 2025-05 | — |
| 118 | Gemini 1.5 Pro (Sept 2024) | Google DeepMind | 131.7 | — | 0.572 | 2024-09 | — |
| 119 | Gemini 2.0 Flash Thinking (Jan 2025) | Google DeepMind | 135.4 | — | 0.571 | 2025-01 | — |
| 120 | Qwen3-8B OPEN | Alibaba | 136.2 | — | 0.568 | 2025-04 | — |
| 121 | DeepSeek-V3 OPEN | DeepSeek | 132.3 | — | 0.565 | 2024-12 | — |
| 122 | Qwen2.5-Max (25 Jan 2025) | Alibaba | 132.5 | — | 0.561 | 2025-01 | — |
| 123 | Magistral Small 1.0 OPEN | Mistral AI | 133.2 | — | 0.561 | 2025-06 | — |
| 124 | Phi-4 OPEN | Microsoft Research | 130.4 | — | 0.561 | 2024-12 | — |
| 125 | DeepSeek-R1-Distill-Llama-70B OPEN | DeepSeek | — | — | 0.557 | 2025-01 | — |
| 126 | Qwen3-30B-A3B-Instruct (Jul 2025) OPEN | Alibaba | 137.4 | — | 0.556 | 2025-07 | — |
| 127 | Claude 3.5 Sonnet (October 2024) | Anthropic | 133.6 | — | 0.553 | 2024-10 | — |
| 128 | Claude 3.5 Sonnet | Anthropic | 130.0 | — | 0.540 | 2024-06 | — |
| 129 | Grok-2 (Dec 2024) | xAI | 130.5 | — | 0.538 | 2024-12 | — |
| 130 | None (qwen3-4b) | Alibaba | — | — | 0.523 | 2025-04 | — |
| 131 | Llama 4 Scout OPEN | Meta AI | 129.6 | — | 0.518 | 2025-04 | — |
| 132 | Mistral Large 2 (Nov 2024) OPEN | Mistral AI | 128.5 | — | 0.513 | 2024-11 | — |
| 133 | Llama 3.1-405B (Instruct) OPEN | Meta AI | 128.8 | — | 0.509 | 2024-07 | — |
| 134 | o1-preview | OpenAI | 134.8 | — | 0.503 | 2024-09 | — |
| 135 | GPT-4o (Aug 2024) | OpenAI | 128.8 | — | 0.492 | 2024-08 | — |
| 136 | Qwen2.5-72B (Instruct) OPEN | Alibaba | 129.0 | — | 0.491 | 2024-09 | — |
| 137 | Mistral Small 3.2 (mistral-small-3.2-2506) OPEN | Mistral AI | 131.7 | — | 0.491 | 2025-06 | — |
| 138 | Mistral Large 2 (Jul 2024) OPEN | Mistral AI | 127.5 | — | 0.490 | 2024-07 | — |
| 139 | GPT-4.1 nano | OpenAI | 129.6 | — | 0.489 | 2025-04 | $0.10 / $0.40 |
| 140 | GPT-4o (May 2024) | OpenAI | 129.0 | — | 0.489 | 2024-05 | $5.00 / $15.00 |
| 141 | Qwen Plus (01 25) | Alibaba | — | — | 0.481 | 2025-01 | — |
| 142 | GPT-4o (Nov 2024) | OpenAI | 128.8 | 0.310 | 0.479 | 2024-11 | — |
| 143 | Gemma 3 27B OPEN | Google DeepMind | 130.0 | — | 0.477 | 2025-03 | — |
| 144 | Magistral Small 1.2 OPEN | Mistral AI | 131.4 | — | 0.476 | 2025-09 | — |
| 145 | Mistral Small 3.1 (mistral-small-2503) OPEN | Mistral AI | 127.5 | — | 0.475 | 2025-03 | — |
| 146 | Llama 3.3 70B OPEN | Meta AI | 127.3 | — | 0.474 | 2024-12 | — |
| 147 | Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) | Google DeepMind | 129.4 | — | 0.473 | 2024-09 | — |
| 148 | Mistral Small 3 (mistral-small-3-2501) OPEN | Mistral AI | 127.1 | — | 0.473 | 2025-01 | — |
| 149 | Claude 3 Opus | Anthropic | 126.9 | — | 0.472 | 2024-02 | — |
| 150 | GPT-4 Turbo (Apr 2024) | OpenAI | 127.2 | — | 0.466 | 2024-04 | $10.00 / $30.00 |
| 151 | Tulu 3 (Tülu 3) 70B OPEN | Allen Institute for AI | — | — | 0.463 | 2024-11 | — |
| 152 | Qwen2.5-32B OPEN | Alibaba | 128.5 | — | 0.461 | 2024-09 | — |
| 153 | Gemini 1.5 Pro (May 2024) | Google DeepMind | 126.9 | — | 0.459 | 2024-05 | — |
| 154 | None (qwen3-4b-instruct-2507) | — | — | — | 0.458 | 2025-08 | — |
| 155 | Mistral Small 3 (mistral-small-2501) OPEN | Mistral AI | 127.1 | — | 0.453 | 2025-01 | — |
| 156 | DeepSeek-R1-Distill-Qwen-14B OPEN | DeepSeek | 135.4 | — | 0.447 | 2025-01 | — |
| 157 | Llama 3.1-70B OPEN | Meta AI | 125.9 | — | 0.442 | 2024-07 | — |
| 158 | WizardLM-2 8x22B OPEN | Microsoft | — | — | 0.434 | 2024-04 | — |
| 159 | GPT-4 Turbo (Jan 2024, 1106 Preview) | OpenAI | 126.5 | — | 0.424 | 2023-11 | $10.00 / $30.00 stale |
| 160 | GPT-4 Turbo (Jan 2024, 0125 Preview) | OpenAI | 126.5 | — | 0.423 | 2024-01 | $10.00 / $30.00 stale |
| 161 | Mistral Small 3.1 (mistral-small-3.1-2503) OPEN | Mistral AI | 127.5 | — | 0.419 | 2025-03 | — |
| 162 | Qwen-Turbo | Alibaba | — | — | 0.418 | 2024-11 | — |
| 163 | Llama 3.2 90B OPEN | Meta AI | 125.5 | — | 0.410 | 2024-09 | — |
| 164 | Qwen2-72B OPEN | Alibaba | 125.3 | — | 0.408 | 2024-06 | — |
| 165 | Claude 3 Sonnet | Anthropic | 120.7 | — | 0.406 | 2024-02 | — |
| 166 | Llama 3-70B (Instruct) OPEN | Meta AI | 122.9 | — | 0.406 | 2024-04 | — |
| 167 | Gemini 1.5 Flash (May 2024) (gemini-1.5-flash-001) | Google DeepMind | 122.6 | — | 0.404 | 2024-05 | — |
| 168 | Gemma 3 12B OPEN | Google DeepMind | 123.5 | — | 0.395 | 2025-03 | — |
| 169 | Mistral Large | Mistral AI | 122.0 | — | 0.388 | 2024-02 | — |
| 170 | Claude 3.5 Haiku | Anthropic | 127.2 | — | 0.381 | 2024-10 | — |
| 171 | None (qwen3-1.7b) | Alibaba | — | — | 0.380 | 2025-04 | — |
| 172 | GPT-4o mini | OpenAI | 126.6 | — | 0.377 | 2024-07 | $0.15 / $0.60 |
| 173 | Hermes 2 Theta Llama-3 70B OPEN | Nous Research | — | — | 0.375 | 2024-06 | — |
| 174 | Gemma 2 27B (It) OPEN | Google DeepMind | 122.0 | — | 0.365 | 2024-06 | — |
| 175 | Claude 3 Haiku | Anthropic | 118.3 | — | 0.363 | 2024-03 | — |
| 176 | GPT-4 (Mar 2023) | OpenAI | 125.9 | — | 0.357 | 2023-03 | $30.00 / $60.00 stale |
| 177 | Qwen2.5-7B OPEN | Alibaba | 118.4 | — | 0.355 | 2024-09 | — |
| 178 | Claude 2 | Anthropic | 120.1 | — | 0.347 | 2023-07 | — |
| 179 | Mixtral 8x22B (Open) OPEN | Mistral AI | 122.0 | — | 0.341 | 2024-04 | — |
| 180 | Gemini 1.0 Pro | Google DeepMind | 117.0 | — | 0.340 | 2023-12 | — |
| 181 | Eurus-2-7B-PRIME OPEN | Tsinghua University | — | — | 0.339 | 2024-12 | — |
| 182 | None (DeepSeek-R1-Distill-Qwen-1.5B) | DeepSeek | — | — | 0.336 | 2025-01 | — |
| 183 | Gemini 1.5 Flash 8B | Google DeepMind | — | — | 0.330 | 2024-10 | — |
| 184 | Claude 2.1 | Anthropic | 119.2 | — | 0.330 | 2023-11 | — |
| 185 | DBRX OPEN | Databricks | — | — | 0.329 | 2024-03 | — |
| 186 | Yi-1.5-34B OPEN | 01.AI | — | — | 0.320 | 2024-05 | — |
| 187 | Qwen1.5-32B (Chat) OPEN | Alibaba | — | — | 0.307 | 2024-04 | — |
| 188 | GPT-4 (Jun 2023) | OpenAI | 123.1 | — | 0.307 | 2023-06 | $30.00 / $60.00 |
| 189 | Mixtral 8x7B (Instruct v0.1) OPEN | Mistral AI | 118.4 | — | 0.306 | 2023-12 | — |
| 190 | Mistral NeMo (Open) OPEN | Mistral AI | 118.6 | — | 0.299 | 2024-07 | — |
| 191 | Mixtral 8x7B (Open) OPEN | Mistral AI | 118.4 | — | 0.298 | 2023-12 | — |
| 192 | Qwen1.5-72B OPEN | Alibaba | — | — | 0.288 | 2024-02 | — |
| 193 | None (granite-4.0-micro) | — | — | — | 0.283 | 2025-10 | — |
| 194 | GPT-3.5 Turbo (Nov 2023) | OpenAI | 118.5 | — | 0.280 | 2023-11 | $1.00 / $2.00 |
| 195 | phi-3-medium 14B OPEN | Microsoft | 121.2 | — | 0.276 | 2024-04 | — |
| 196 | Gemma 2 9B (It) OPEN | Google DeepMind | 119.8 | — | 0.275 | 2024-06 | — |
| 197 | GPT-3.5 Turbo (Jan 2024) | OpenAI | 115.6 | — | 0.272 | 2024-01 | $0.50 / $1.50 |
| 198 | Ministral 8B OPEN | Mistral AI | — | — | 0.271 | 2024-10 | — |
| 199 | Llama 3.1-8B OPEN | Meta AI | 116.5 | — | 0.270 | 2024-07 | — |
| 200 | Llama 2-70B (Chat) OPEN | Meta AI | 113.6 | — | 0.263 (hf) | 2023-07 | — |
| 201 | Llama 3-8B (Instruct) OPEN | Meta AI | 116.3 | — | 0.261 | 2024-04 | — |
| 202 | Ministral 3B (16 Oct 2024) | Mistral AI | 118.1 | — | 0.253 | 2024-10 | — |
| 203 | DeepSeek LLM 67B (Chat) OPEN | DeepSeek | 110.6 | — | 0.246 | 2023-11 | — |
| 204 | None (granite-4.0-1b) | — | — | — | 0.240 | 2025-10 | — |
| 205 | Llama 3.2 1B OPEN | Meta AI | 102.4 | — | 0.239 | 2024-09 | — |
| 206 | Gemma 3 4B OPEN | Google DeepMind | 116.0 | — | 0.232 | 2025-03 | — |
| 207 | None (gemma-3-1b-it) | Google DeepMind | — | — | 0.199 | 2025-03 | — |
| 208 | Mistral 7B v0.3 (Instruct) OPEN | Mistral AI | 108.8 | — | 0.152 | 2024-05 | — |
| 209 | Yi-34B (Chat) OPEN | 01.AI | 117.3 | — | 0.147 | 2023-11 | — |
| 210 | Mistral 7B v0.3 (Open) OPEN | Mistral AI | 108.8 | — | 0.132 | 2023-09 | — |
| 211 | None (granite-4.0-350m) | — | — | — | 0.112 | 2025-10 | — |
| 212 | None (deepseek-r1-0528-qwen3-8b) | — | — | — | 0.093 | 2025-05 | — |
No Epoch-run agentic benchmark is ingested yet. Epoch redistributes several agentic third-party leaderboards (apex_agents_external, the_agent_company_external, os_world_external and others) inside the same bundle, but each needs its own licensing review before Xentir reads it — see Data Sources. This tab will populate once one clears.
Scroll to see more →
| Rank | Model | Provider | Overall | Coding | Reasoning | Released | Price |
|---|---|---|---|---|---|---|---|
| 1 | Kimi K3 OPEN | Moonshot | 157.6 | — | 0.931 (max) | 2026-07 | — |
| 2 | DeepSeek V4 Pro 0813 OPEN | DeepSeek | 155.5 | — | 0.917 (max) | 2026-08 | — |
| 3 | DeepSeek V4 Flash 0731 OPEN | DeepSeek | 154.5 | — | 0.910 (max) | 2026-07 | — |
| 4 | GLM-5.2 OPEN | Z.ai (Zhipu AI) | 151.9 | 0.787 (max) | 0.919 (max) | 2026-06 | — |
| 5 | GLM-5.3-Flash OPEN | Z.ai (Zhipu AI) | 151.4 | — | 0.902 (max) | 2026-08 | — |
| 6 | Kimi K2.6 OPEN | Moonshot | 151.0 | 0.767 | 0.908 | 2026-04 | — |
| 7 | Inkling-Small OPEN | Thinking Machines | 150.2 | — | 0.885 (xhigh) | 2026-07 | — |
| 8 | Kimi K2.7 Code OPEN | Moonshot | 150.1 | — | 0.879 | 2026-06 | — |
| 9 | GLM-5.1 OPEN | Z.ai (Zhipu AI) | 149.7 | 0.742 | 0.899 | 2026-04 | — |
| 10 | DeepSeek-V4-Pro OPEN | DeepSeek | 149.1 | 0.776 (max) | 0.909 (high) | 2026-04 | — |
| 11 | Inkling OPEN | Thinking Machines | 148.6 | — | 0.883 (xhigh) | 2026-07 | — |
| 12 | Kimi K2.5 OPEN | Moonshot | 148.0 | 0.738 | 0.876 (fireworks) | 2026-01 | — |
| 13 | Qwen3.5 397B-A17B OPEN | Alibaba | 147.0 | — | 0.864 (none) | 2026-02 | — |
| 14 | MiniMax-M2.5 OPEN | MiniMax | 146.5 | — | — | 2026-02 | — |
| 15 | Qwen3.6 27B OPEN | Alibaba | 146.5 | — | 0.859 | 2026-04 | — |
| 16 | MiniMax-M3 OPEN | MiniMax | 146.5 | — | 0.909 | 2026-06 | — |
| 17 | Nemotron 3 Ultra OPEN | NVIDIA | 146.3 | — | 0.854 | 2026-06 | — |
| 18 | DeepSeek-V3.2 (Chat) OPEN | DeepSeek | 146.2 | — | 0.712 | 2025-12 | — |
| 19 | DeepSeek-V3.2 (Reasoner) OPEN | DeepSeek | 146.2 | — | 0.834 | 2025-12 | — |
| 20 | DeepSeek-V4-Flash OPEN | DeepSeek | 146.1 | — | — | 2026-04 | — |
| 21 | GLM-5 OPEN | Z.ai (Zhipu AI) | 145.8 | 0.721 | 0.878 | 2026-02 | — |
| 22 | MiniMax-M2.7 OPEN | MiniMax | 145.8 | — | — | 2026-03 | — |
| 23 | Kimi K2 Thinking OPEN | Moonshot | 145.8 | — | — | 2025-11 | — |
| 24 | Kimi K2 Thinking (Turbo) OPEN | Moonshot | 145.8 | — | 0.842 | 2025-11 | — |
| 25 | DeepSeek-V3.2-Exp OPEN | DeepSeek | 145.0 | — | — | 2025-09 | — |
| 26 | Qwen3-235B-A22B-Thinking (Jul 2025) OPEN | Alibaba | 143.9 | — | 0.801 | 2025-07 | — |
| 27 | Qwen 3.6 35B-A3B OPEN | Alibaba | 143.9 | — | 0.848 (none) | 2026-04 | — |
| 28 | GLM-4.7 OPEN | Z.ai (Zhipu AI) | 143.5 | — | 0.833 | 2025-12 | — |
| 29 | Gemma 4 31B IT OPEN | Google DeepMind | 142.7 | — | 0.758 (minimal) | 2026-04 | — |
| 30 | Qwen3.5-35B-A3B OPEN | Alibaba | 142.5 | — | 0.835 | 2026-02 | — |
| 31 | Gemma 4 26B A4B OPEN | Google DeepMind | 141.9 | — | — | 2026-04 | — |
| 32 | Gemma 4 26B A4B (It) OPEN | Google DeepMind | 141.9 | — | 0.732 (minimal) | 2026-04 | — |
| 33 | DeepSeek-R1 (May 2025) OPEN | DeepSeek | 141.3 | — | 0.763 | 2025-05 | — |
| 34 | Mistral Medium 3.5 OPEN | Mistral AI | 141.3 | — | — | 2026-04 | — |
| 35 | GLM-4.6 OPEN | Z.ai (Zhipu AI) | 140.8 | — | — | 2025-09 | — |
| 36 | Kimi K2 (Jul 2025, 0711 Preview) OPEN | Moonshot | 140.1 | — | — | 2025-07 | — |
| 37 | Kimi K2 (Jul 2025, Instruct) OPEN | Moonshot | 140.1 | — | — | 2025-07 | — |
| 38 | gpt-oss-120b OPEN | OpenAI | 140.1 | — | 0.758 (high-openai) | 2025-08 | — |
| 39 | DeepSeek-V3.1 OPEN | DeepSeek | 139.9 | — | — | 2025-08 | — |
| 40 | Qwen3-30B-A3B-Thinking (Jul 2025) OPEN | Alibaba | 139.6 | — | 0.701 | 2025-07 | — |
| 41 | Qwen3.5-9B OPEN | Alibaba | 139.4 | — | 0.790 | 2026-02 | — |
| 42 | Qwen3-235B-A22B OPEN | Alibaba | 139.3 | — | 0.707 | 2025-04 | — |
| 43 | DeepSeek-R1 OPEN | DeepSeek | 139.0 | — | 0.692 | 2025-01 | — |
| 44 | Qwen3-235B-A22B-Instruct (Jul 2025) OPEN | Alibaba | 138.9 | — | — | 2025-07 | — |
| 45 | Qwen3-32B OPEN | Alibaba | 138.5 | — | 0.657 | 2025-04 | — |
| 46 | Qwen3-14B OPEN | Alibaba | 138.2 | — | 0.638 | 2025-04 | — |
| 47 | gpt-oss-20b OPEN | OpenAI | 137.8 | — | 0.608 (medium) | 2025-08 | — |
| 48 | QwQ-32B OPEN | Alibaba | 137.6 | — | 0.653 | 2025-03 | — |
| 49 | DeepSeek-R1-Distill-Qwen-32B OPEN | DeepSeek | 137.4 | — | 0.641 | 2025-01 | — |
| 50 | Qwen3-30B-A3B-Instruct (Jul 2025) OPEN | Alibaba | 137.4 | — | 0.556 | 2025-07 | — |
| 51 | Qwen3-30B-A3B OPEN | Alibaba | 136.2 | — | 0.617 | 2025-04 | — |
| 52 | Qwen3-8B OPEN | Alibaba | 136.2 | — | 0.568 | 2025-04 | — |
| 53 | DeepSeek-V3 (Mar 2025) OPEN | DeepSeek | 135.9 | — | 0.676 | 2025-03 | — |
| 54 | DeepSeek-R1-Distill-Qwen-14B OPEN | DeepSeek | 135.4 | — | 0.447 | 2025-01 | — |
| 55 | Magistral Small 1.0 OPEN | Mistral AI | 133.2 | — | 0.561 | 2025-06 | — |
| 56 | DeepSeek-V3 OPEN | DeepSeek | 132.3 | — | 0.565 | 2024-12 | — |
| 57 | DeepSeek-V3 (Base) OPEN | DeepSeek | 132.3 | — | — | 2024-12 | — |
| 58 | Llama 4 Maverick OPEN | Meta AI | 132.2 | — | — | 2025-04 | — |
| 59 | Llama 4 Maverick (FP8) OPEN | Meta AI | 132.2 | — | 0.670 | 2025-04 | — |
| 60 | Mistral Small 3.2 (mistral-small-3.2-2506) OPEN | Mistral AI | 131.7 | — | 0.491 | 2025-06 | — |
| 61 | Mistral Small 3.2 (mistral-small-2506) OPEN | Mistral AI | 131.7 | — | — | 2025-06 | — |
| 62 | Magistral Small 1.2 OPEN | Mistral AI | 131.4 | — | 0.476 | 2025-09 | — |
| 63 | Phi-4 OPEN | Microsoft Research | 130.4 | — | 0.561 | 2024-12 | — |
| 64 | Phi-4 (phi4:14b q8 0) OPEN | Microsoft Research | 130.4 | — | — | 2024-12 | — |
| 65 | Gemma 3 27B OPEN | Google DeepMind | 130.0 | — | 0.477 | 2025-03 | — |
| 66 | Llama 4 Scout OPEN | Meta AI | 129.6 | — | 0.518 | 2025-04 | — |
| 67 | Qwen2.5-72B OPEN | Alibaba | 129.0 | — | — | 2024-09 | — |
| 68 | Qwen2.5-72B (Instruct) OPEN | Alibaba | 129.0 | — | 0.491 | 2024-09 | — |
| 69 | Qwen2.5-72B (Vl Instruct) OPEN | Alibaba | 129.0 | — | — | 2024-09 | — |
| 70 | Llama 3.1-405B OPEN | Meta AI | 128.8 | — | — | 2024-07 | — |
| 71 | Llama 3.1-405B (Instruct) OPEN | Meta AI | 128.8 | — | 0.509 | 2024-07 | — |
| 72 | Llama 3.1-405B (Instruct q4 K) OPEN | Meta AI | 128.8 | — | — | 2024-07 | — |
| 73 | Qwen2.5-32B OPEN | Alibaba | 128.5 | — | 0.461 | 2024-09 | — |
| 74 | Qwen2.5-32B (Coder Q8 0 Gguf) OPEN | Alibaba | 128.5 | — | — | 2024-09 | — |
| 75 | Mistral Large 2 (Nov 2024) OPEN | Mistral AI | 128.5 | — | 0.513 | 2024-11 | — |
| 76 | Mistral Large 2 (Nov 2024, Instruct) OPEN | Mistral AI | 128.5 | — | — | 2024-11 | — |
| 77 | Mistral Large 2 (Jul 2024) OPEN | Mistral AI | 127.5 | — | 0.490 | 2024-07 | — |
| 78 | Mistral Large 2 (Jul 2024, Instruct) OPEN | Mistral AI | 127.5 | — | — | 2024-07 | — |
| 79 | Mistral Small 3.1 (mistral-small-3.1-2503) OPEN | Mistral AI | 127.5 | — | 0.419 | 2025-03 | — |
| 80 | Mistral Small 3.1 (mistral-small-2503) OPEN | Mistral AI | 127.5 | — | 0.475 | 2025-03 | — |
| 81 | Llama 3.3 70B OPEN | Meta AI | 127.3 | — | 0.474 | 2024-12 | — |
| 82 | Mistral Small 3 (mistral-small-3-2501) OPEN | Mistral AI | 127.1 | — | 0.473 | 2025-01 | — |
| 83 | Mistral Small 3 (mistral-small-2501) OPEN | Mistral AI | 127.1 | — | 0.453 | 2025-01 | — |
| 84 | Llama 3.1-70B OPEN | Meta AI | 125.9 | — | 0.442 | 2024-07 | — |
| 85 | Llama 3.2 90B OPEN | Meta AI | 125.5 | — | 0.410 | 2024-09 | — |
| 86 | Qwen2-72B OPEN | Alibaba | 125.3 | — | 0.408 | 2024-06 | — |
| 87 | DeepSeek-V2 (MoE-236B, May 2024) OPEN | DeepSeek | 124.8 | — | — | 2024-05 | — |
| 88 | Gemma 3 12B OPEN | Google DeepMind | 123.5 | — | 0.395 | 2025-03 | — |
| 89 | Llama 3-70B OPEN | Meta AI | 122.9 | — | — | 2024-04 | — |
| 90 | Llama 3-70B (Instruct) OPEN | Meta AI | 122.9 | — | 0.406 | 2024-04 | — |
| 91 | Gemma 2 27B OPEN | Google DeepMind | 122.0 | — | — | 2024-06 | — |
| 92 | Gemma 2 27B (It) OPEN | Google DeepMind | 122.0 | — | 0.365 | 2024-06 | — |
| 93 | Gemma 2 27B (Instruct q8 0) OPEN | Google DeepMind | 122.0 | — | — | 2024-06 | — |
| 94 | Mixtral 8x22B (Instruct v0.1) OPEN | Mistral AI | 122.0 | — | — | 2024-04 | — |
| 95 | Mixtral 8x22B (v0.1) OPEN | Mistral AI | 122.0 | — | — | 2024-04 | — |
| 96 | Mixtral 8x22B (Open) OPEN | Mistral AI | 122.0 | — | 0.341 | 2024-04 | — |
| 97 | phi-3-small 7.4B OPEN | Microsoft | 121.8 | — | — | 2024-04 | — |
| 98 | phi-3-medium 14B OPEN | Microsoft | 121.2 | — | 0.276 | 2024-04 | — |
| 99 | Gemma 2 9B OPEN | Google DeepMind | 119.8 | — | — | 2024-06 | — |
| 100 | Gemma 2 9B (It) OPEN | Google DeepMind | 119.8 | — | 0.275 | 2024-06 | — |
| 101 | Qwen2.5-Coder-32B OPEN | Alibaba | 119.4 | — | — | 2024-09 | — |
| 102 | Command R+ OPEN | Cohere | 119.2 | — | — | 2024-08 | — |
| 103 | Mistral NeMo (Base) OPEN | Mistral AI | 118.6 | — | — | 2024-07 | — |
| 104 | Mistral NeMo (Instruct) OPEN | Mistral AI | 118.6 | — | — | 2024-07 | — |
| 105 | Mistral NeMo (Open) OPEN | Mistral AI | 118.6 | — | 0.299 | 2024-07 | — |
| 106 | Qwen2.5-7B OPEN | Alibaba | 118.4 | — | 0.355 | 2024-09 | — |
| 107 | Mixtral 8x7B (Instruct v0.1) OPEN | Mistral AI | 118.4 | — | 0.306 | 2023-12 | — |
| 108 | Mixtral 8x7B (v0.1) OPEN | Mistral AI | 118.4 | — | — | 2023-12 | — |
| 109 | Mixtral 8x7B (Open) OPEN | Mistral AI | 118.4 | — | 0.298 | 2023-12 | — |
| 110 | Yi-34B OPEN | 01.AI | 117.3 | — | — | 2023-11 | — |
| 111 | Yi-34B (Chat) OPEN | 01.AI | 117.3 | — | 0.147 | 2023-11 | — |
| 112 | phi-3-mini 3.8B (4k) OPEN | Microsoft | 117.2 | — | — | 2024-04 | — |
| 113 | phi-3-mini 3.8B (128k) OPEN | Microsoft | 117.2 | — | — | 2024-04 | — |
| 114 | Stable Beluga 2 OPEN | Stability AI | 117.0 | — | — | 2023-07 | — |
| 115 | Llama 3.1-8B OPEN | Meta AI | 116.5 | — | 0.270 | 2024-07 | — |
| 116 | Llama 3-8B OPEN | Meta AI | 116.3 | — | — | 2024-04 | — |
| 117 | Llama 3-8B (Instruct) OPEN | Meta AI | 116.3 | — | 0.261 | 2024-04 | — |
| 118 | Gemma 3 4B OPEN | Google DeepMind | 116.0 | — | 0.232 | 2025-03 | — |
| 119 | Llama 2-70B (Chat) OPEN | Meta AI | 113.6 | — | 0.263 (hf) | 2023-07 | — |
| 120 | Llama 2-70B (Hf) OPEN | Meta AI | 113.6 | — | — | 2023-07 | — |
| 121 | Qwen2.5-Coder (7B) OPEN | Alibaba | 113.0 | — | — | 2024-09 | — |
| 122 | Qwen2.5-Coder (7B, Instruct) OPEN | Alibaba | 113.0 | — | — | 2024-09 | — |
| 123 | Qwen-14B OPEN | Alibaba | 112.8 | — | — | 2023-09 | — |
| 124 | Qwen-14B (Chat) OPEN | Alibaba | 112.8 | — | — | 2023-09 | — |
| 125 | Mistral 7B v0.1 (Instruct) OPEN | Mistral AI | 112.0 | — | — | 2023-09 | — |
| 126 | Mistral 7B v0.1 OPEN | Mistral AI | 112.0 | — | — | 2023-09 | — |
| 127 | Falcon-180B OPEN | Technology Innovation Institute | 111.9 | — | — | 2023-09 | — |
| 128 | Gemma 7B OPEN | Google DeepMind | 111.8 | — | — | 2024-02 | — |
| 129 | DeepSeek LLM 67B (Base) OPEN | DeepSeek | 110.6 | — | — | 2023-11 | — |
| 130 | DeepSeek LLM 67B (Chat) OPEN | DeepSeek | 110.6 | — | 0.246 | 2023-11 | — |
| 131 | LLaMA-65B OPEN | Meta AI | 109.9 | — | — | 2023-02 | — |
| 132 | Falcon 2 11B OPEN | Technology Innovation Institute | 109.3 | — | — | 2024-05 | — |
| 133 | Mistral 7B v0.3 (Instruct) OPEN | Mistral AI | 108.8 | — | 0.152 | 2024-05 | — |
| 134 | Mistral 7B v0.3 OPEN | Mistral AI | 108.8 | — | — | 2024-05 | — |
| 135 | Mistral 7B v0.3 (Open) OPEN | Mistral AI | 108.8 | — | 0.132 | 2023-09 | — |
| 136 | Phi-2 OPEN | Microsoft | 107.7 | — | — | 2023-12 | — |
| 137 | LLaMA-33B OPEN | Meta AI | 107.1 | — | — | 2023-02 | — |
| 138 | Qwen-7B OPEN | Alibaba | 106.5 | — | — | 2023-09 | — |
| 139 | Llama 2-13B OPEN | Meta AI | 105.9 | — | — | 2023-07 | — |
| 140 | Llama 2-13B (Chat) OPEN | Meta AI | 105.9 | — | — | 2023-07 | — |
| 141 | StarCoder 2 15B OPEN | Hugging Face | 104.7 | — | — | 2024-02 | — |
| 142 | Yi 6B OPEN | 01.AI | 104.5 | — | — | 2023-11 | — |
| 143 | Yi 6B (Chat) OPEN | 01.AI | 104.5 | — | — | 2023-11 | — |
| 144 | Falcon-40B OPEN | Technology Innovation Institute | 104.1 | — | — | 2023-05 | — |
| 145 | Falcon-40B (Instruct) OPEN | Technology Innovation Institute | 104.1 | — | — | 2023-05 | — |
| 146 | Baichuan2-13B OPEN | Baichuan | 102.9 | — | — | 2023-09 | — |
| 147 | Qwen2.5-Coder (1.5B) OPEN | Alibaba | 102.7 | — | — | 2024-09 | — |
| 148 | Llama 3.2 1B OPEN | Meta AI | 102.4 | — | 0.239 | 2024-09 | — |
| 149 | MPT-30B OPEN | MosaicML | 100.3 | — | — | 2023-06 | — |
| 150 | MPT-30B (Instruct) OPEN | MosaicML | 100.3 | — | — | 2023-06 | — |
| 151 | LLaMA-13B OPEN | Meta AI | 100.2 | — | — | 2023-02 | — |
| 152 | Llama 2-7B OPEN | Meta AI | 98.7 | — | — | 2023-07 | — |
| 153 | Llama 2-7B (Chat) OPEN | Meta AI | 98.7 | — | — | 2023-07 | — |
| 154 | LLaMA-7B OPEN | Meta AI | 96.2 | — | — | 2023-02 | — |
| 155 | Baichuan 2-7B OPEN | Baichuan | 95.9 | — | — | 2023-09 | — |
| 156 | DeepSeek Coder 33B (Base) OPEN | DeepSeek | 95.9 | — | — | 2023-11 | — |
| 157 | DeepSeek Coder 33B (Instruct) OPEN | DeepSeek | 95.9 | — | — | 2023-11 | — |
| 158 | Falcon-7B OPEN | Technology Innovation Institute | 94.6 | — | — | 2023-04 | — |
| 159 | MPT-7B OPEN | MosaicML | 94.1 | — | — | 2023-05 | — |
| 160 | MPT-7B (Instruct) OPEN | MosaicML | 94.1 | — | — | 2023-05 | — |
| 161 | Gemma 2B OPEN | Google DeepMind | 93.7 | — | — | 2024-02 | — |
| 162 | StarCoder 2 7B OPEN | Hugging Face | 93.1 | — | — | 2024-02 | — |
| 163 | XGen-7B OPEN | Salesforce | 92.9 | — | — | 2023-06 | — |
| 164 | Phi-1.5 OPEN | Microsoft | 91.0 | — | — | 2023-09 | — |
| 165 | Baichuan1-7B OPEN | Baichuan | 89.9 | — | — | 2023-06 | — |
| 166 | Dolly 2.0-12b OPEN | Databricks | 89.1 | — | — | 2023-04 | — |
| 167 | DeepSeek Coder 6.7B (Base) OPEN | DeepSeek | 89.0 | — | — | 2023-11 | — |
| 168 | DeepSeek Coder 6.7B (Instruct) OPEN | DeepSeek | 89.0 | — | — | 2023-11 | — |
| 169 | DeepSeek Coder 6.7B (Base v1.5) OPEN | DeepSeek | 89.0 | — | — | 2023-11 | — |
| 170 | StarCoder 2 3B OPEN | Hugging Face | 88.2 | — | — | 2024-02 | — |
| 171 | Cerebras-GPT-13B OPEN | Cerebras Systems | 82.6 | — | — | 2023-03 | — |
| 172 | DeepSeek Coder 1.3B (Base) OPEN | DeepSeek | 62.5 | — | — | 2023-11 | — |
| 173 | DeepSeek Coder 1.3B (Instruct) OPEN | DeepSeek | 62.5 | — | — | 2023-11 | — |
| Benchmark | Score |
|---|