# AA-GPQA Diamond leaderboard

Knowledge benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/knowledge-aa-gpqa-diamond

Artificial Analysis GPQA Diamond. Every model the catalog carries a published AA-GPQA Diamond value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Accuracy |
| Tasks | Graduate-level science questions |
| Difficulty | Graduate-level science reasoning |
| Published by | [Artificial Analysis GPQA Diamond Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gpqa-diamond) |

An Artificial Analysis GPQA Diamond score.

## AA-GPQA Diamond ranking

206 models with a published AA-GPQA Diamond value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Accuracy | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 96.1 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 95.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 94.9 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 3.7 Flash](https://modelscale.dev/models/gemini-3-7-flash) | Google | 94.5 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 94.1 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 94.1 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 93.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 93.5 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 93.5 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Muse Spark 1.3](https://modelscale.dev/models/muse-spark-1-3) | Meta | 93.5 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 93.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Grok 4.5](https://modelscale.dev/models/grok-4-5) | xAI | 93.1 | Observed 2026-11-21 · source benchlm:models |
| 13 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 92.9 | Observed 2026-11-21 · source benchlm:models |
| 14 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | 92.8 | Observed 2026-11-21 · source benchlm:models |
| 14 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 92.8 | Last good 2026-11-18 · source benchlm:models |
| 14 | [Gemini 3.6 Flash](https://modelscale.dev/models/gemini-3-6-flash) | Google | 92.8 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Qwen3.8 Max Preview](https://modelscale.dev/models/qwen3-8-max-preview) | Alibaba | 92.8 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 92.6 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | 92.5 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 92.3 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Qwen3.8-Flash-Next](https://modelscale.dev/models/qwen3-8-flash-next) | Alibaba | 92.3 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 92.2 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 92.0 | Observed 2026-11-21 · source benchlm:models |
| 23 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 92.0 | Observed 2026-11-21 · source benchlm:models |
| 25 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 91.7 | Observed 2026-11-21 · source benchlm:models |
| 26 | [GPT-5.3 Codex](https://modelscale.dev/models/gpt-5-3-codex) | OpenAI | 91.5 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 91.4 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Claude Opus 4.7 (Adaptive)](https://modelscale.dev/models/claude-opus-4-7-max) | Anthropic | 91.4 | Last good 2026-11-18 · source benchlm:models |
| 29 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | 91.2 | Last good 2026-10-23 · source benchlm:models |
| 30 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 91.1 | Observed 2026-11-21 · source benchlm:models |
| 30 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | 91.1 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 91.1 | Observed 2026-11-21 · source benchlm:models |
| 33 | [DeepSeek V4 Flash 0731](https://modelscale.dev/models/deepseek-v4-flash-max) | DeepSeek | 90.8 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 90.8 | Observed 2026-11-21 · source benchlm:models |
| 35 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | 90.5 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Muse Spark 1.2](https://modelscale.dev/models/muse-spark-1-2) | Meta | 90.4 | Observed 2026-11-21 · source benchlm:models |
| 37 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 90.3 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | 90.1 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 90.0 | Observed 2026-11-21 · source benchlm:models |
| 40 | [GPT-5.2-Codex](https://modelscale.dev/models/gpt-5-2-codex) | OpenAI | 89.9 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Muse Spark 1.1](https://modelscale.dev/models/muse-spark-1-1) | Meta | 89.8 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Hy3](https://modelscale.dev/models/hy3) | Tencent | 89.7 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Hy3 Preview](https://modelscale.dev/models/hy3-preview) | Tencent | 89.7 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Claude Opus 4.6 (Adaptive)](https://modelscale.dev/models/claude-opus-4-6-thinking) | Anthropic | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Kimi K2.7 Code](https://modelscale.dev/models/kimi-k2-7-code) | Moonshot AI | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 46 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | 89.5 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | 89.5 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 89.3 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Qwen3.5 397B (Reasoning)](https://modelscale.dev/models/qwen3-5-397b-reasoning) | Alibaba | 89.3 | Last good 2026-11-18 · source benchlm:models |
| 50 | [Solar Pro 4](https://modelscale.dev/models/solar-pro-4) | Upstage | 89.1 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Muse Spark Open](https://modelscale.dev/models/muse-spark-open) | Meta | 89.0 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Qwen 3.6 Max (preview)](https://modelscale.dev/models/qwen3-6-max-preview) | Alibaba | 88.8 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Muse Spark](https://modelscale.dev/models/muse-spark) | Meta | 88.4 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 88.2 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 87.9 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Kimi K2.5 (Reasoning)](https://modelscale.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 87.9 | Last good 2026-11-18 · source benchlm:models |
| 57 | [Grok 4](https://modelscale.dev/models/grok-4) | xAI | 87.7 | Observed 2026-11-21 · source benchlm:models |
| 58 | [GPT-5.4 mini](https://modelscale.dev/models/gpt-5-4-mini) | OpenAI | 87.5 | Observed 2026-11-21 · source benchlm:models |
| 59 | [MiniMax M2.7](https://modelscale.dev/models/minimax-m2-7) | MiniMax | 87.4 | Observed 2026-11-21 · source benchlm:models |
| 60 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 87.3 | Observed 2026-11-21 · source benchlm:models |
| 61 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 87.2 | Observed 2026-11-21 · source benchlm:models |
| 62 | [MiMo-V2-Pro](https://modelscale.dev/models/mimo-v2-pro) | Xiaomi | 87.0 | Observed 2026-11-21 · source benchlm:models |
| 63 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | 86.8 | Observed 2026-11-21 · source benchlm:models |
| 64 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 86.7 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Claude Opus 4.5 Thinking](https://modelscale.dev/models/claude-opus-4-5-thinking) | Anthropic | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 65 | [MiMo-V2.5-Pro](https://modelscale.dev/models/mimo-v2-5-pro) | Xiaomi | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Apodex 1.1](https://modelscale.dev/models/apodex-1-1) | Apodex | 86.4 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Apodex 1.1 Mini](https://modelscale.dev/models/apodex-1-1-mini) | Apodex | 86.4 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Ling 3.0 Flash VL](https://modelscale.dev/models/ling-3-0-flash-vl) | InclusionAI | 86.2 | Observed 2026-11-21 · source benchlm:models |
| 70 | [GPT-5.1-Codex](https://modelscale.dev/models/gpt-5-1-codex) | OpenAI | 86.0 | Observed 2026-11-21 · source benchlm:models |
| 70 | [GPT-5.1-Codex-Max](https://modelscale.dev/models/gpt-5-1-codex-max) | OpenAI | 86.0 | Observed 2026-11-21 · source benchlm:models |
| 72 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 85.9 | Observed 2026-11-21 · source benchlm:models |
| 73 | [Qwen3.5-27B](https://modelscale.dev/models/qwen3-5-27b) | Alibaba | 85.8 | Observed 2026-11-21 · source benchlm:models |
| 74 | [A.X K2](https://modelscale.dev/models/a-x-k2) | SK Telecom | 85.7 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Gemma 4 31B](https://modelscale.dev/models/gemma-4-31b) | Google | 85.7 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Qwen3.5-122B-A10B](https://modelscale.dev/models/qwen3-5-122b-a10b) | Alibaba | 85.7 | Observed 2026-11-21 · source benchlm:models |
| 77 | [Ling 3.0 Flash](https://modelscale.dev/models/ling-3-0-flash) | InclusionAI | 85.5 | Observed 2026-11-21 · source benchlm:models |
| 77 | [Ling 3.0 Flash FP8](https://modelscale.dev/models/ling-3-0-flash-fp8) | InclusionAI | 85.5 | Last good 2026-10-08 · source benchlm:models |
| 79 | [GPT-5](https://modelscale.dev/models/gpt-5) | OpenAI | 85.4 | Observed 2026-11-21 · source benchlm:models |
| 79 | [GPT-5 (high)](https://modelscale.dev/models/gpt-5-high) | OpenAI | 85.4 | Last good 2026-11-18 · source benchlm:models |
| 81 | [Grok 4.1 Fast (Reasoning)](https://modelscale.dev/models/grok-4-1-fast-reasoning) | xAI | 85.3 | Observed 2026-11-21 · source benchlm:models |
| 82 | [GLM-5-Turbo](https://modelscale.dev/models/glm-5-turbo) | Z.AI | 84.7 | Observed 2026-11-21 · source benchlm:models |
| 82 | [Grok 4 Fast (Reasoning)](https://modelscale.dev/models/grok-4-fast-reasoning) | xAI | 84.7 | Observed 2026-11-21 · source benchlm:models |
| 84 | [o3-pro](https://modelscale.dev/models/o3-pro) | OpenAI | 84.5 | Observed 2026-11-21 · source benchlm:models |
| 84 | [Qwen3.5-35B-A3B](https://modelscale.dev/models/qwen3-5-35b-a3b) | Alibaba | 84.5 | Observed 2026-11-21 · source benchlm:models |
| 86 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | 84.4 | Observed 2026-11-21 · source benchlm:models |
| 87 | [GPT-5 (medium)](https://modelscale.dev/models/gpt-5-medium) | OpenAI | 84.2 | Last good 2026-11-18 · source benchlm:models |
| 87 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | 84.2 | Observed 2026-11-21 · source benchlm:models |
| 89 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 84.1 | Observed 2026-11-21 · source benchlm:models |
| 90 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 84.0 | Observed 2026-11-21 · source benchlm:models |
| 91 | [Gemini 3.5 Flash-Lite](https://modelscale.dev/models/gemini-3-5-flash-lite) | Google | 83.8 | Observed 2026-11-21 · source benchlm:models |
| 92 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | 83.5 | Observed 2026-11-21 · source benchlm:models |
| 93 | [K-EXAONE 2.0](https://modelscale.dev/models/k-exaone-2-0) | LG AI Research | 82.9 | Observed 2026-11-21 · source benchlm:models |
| 94 | [MiMo-V2-Omni](https://modelscale.dev/models/mimo-v2-omni) | Xiaomi | 82.8 | Observed 2026-11-21 · source benchlm:models |
| 95 | [o3](https://modelscale.dev/models/o3) | OpenAI | 82.7 | Observed 2026-11-21 · source benchlm:models |
| 96 | [GLM-5](https://modelscale.dev/models/glm-5) | Z.AI | 82.0 | Observed 2026-11-21 · source benchlm:models |
| 97 | [GPT-5.4 nano](https://modelscale.dev/models/gpt-5-4-nano) | OpenAI | 81.7 | Observed 2026-11-21 · source benchlm:models |
| 98 | [DeepSeek-R1](https://modelscale.dev/models/deepseek-r1) | DeepSeek | 81.3 | Observed 2026-11-21 · source benchlm:models |
| 99 | [Gemini 3 Flash](https://modelscale.dev/models/gemini-3-flash) | Google | 81.2 | Observed 2026-11-21 · source benchlm:models |
| 100 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 81.0 | Observed 2026-11-21 · source benchlm:models |
| 101 | [Claude 4.1 Opus Thinking](https://modelscale.dev/models/claude-4-1-opus-thinking) | Anthropic | 80.9 | Last good 2026-11-18 · source benchlm:models |
| 101 | [GLM-5V-Turbo](https://modelscale.dev/models/glm-5v-turbo) | Z.AI | 80.9 | Observed 2026-11-21 · source benchlm:models |
| 101 | [Step 3.7 Flash](https://modelscale.dev/models/step-3-7-flash) | StepFun | 80.9 | Observed 2026-11-21 · source benchlm:models |
| 104 | [Nemotron 3 Super 100B](https://modelscale.dev/models/nemotron-3-super-100b) | NVIDIA | 80.0 | Last good 2026-10-08 · source benchlm:models |
| 105 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | 79.9 | Observed 2026-11-21 · source benchlm:models |
| 106 | [Claude 4 Opus Thinking](https://modelscale.dev/models/claude-4-opus-thinking) | Anthropic | 79.6 | Observed 2026-11-21 · source benchlm:models |
| 107 | [Gemma 4 26B A4B](https://modelscale.dev/models/gemma-4-26b-a4b) | Google | 79.2 | Observed 2026-11-21 · source benchlm:models |
| 108 | [o4-mini](https://modelscale.dev/models/o4-mini) | OpenAI | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 109 | [K-Exaone](https://modelscale.dev/models/k-exaone) | LG AI Research | 78.3 | Observed 2026-11-21 · source benchlm:models |
| 110 | [GPT-OSS 120B](https://modelscale.dev/models/gpt-oss-120b) | OpenAI | 78.2 | Observed 2026-11-21 · source benchlm:models |
| 111 | [DeepSeek V3.1 (Reasoning)](https://modelscale.dev/models/deepseek-v3-1-reasoning) | DeepSeek | 77.9 | Last good 2026-11-18 · source benchlm:models |
| 112 | [Claude 3.7 Sonnet Thinking](https://modelscale.dev/models/claude-3-7-sonnet-thinking) | Anthropic | 77.2 | Observed 2026-11-21 · source benchlm:models |
| 113 | [Qwen3.5-4B](https://modelscale.dev/models/qwen3-5-4b) | Alibaba | 77.1 | Observed 2026-11-21 · source benchlm:models |
| 114 | [Mistral Small 4](https://modelscale.dev/models/mistral-small-4) | Mistral | 76.9 | Observed 2026-11-21 · source benchlm:models |
| 114 | [Mistral Small 4 (Reasoning)](https://modelscale.dev/models/mistral-small-4-reasoning) | Mistral | 76.9 | Last good 2026-11-18 · source benchlm:models |
| 116 | [Kimi K2](https://modelscale.dev/models/kimi-k2) | Moonshot AI | 76.6 | Observed 2026-11-21 · source benchlm:models |
| 117 | [o1-preview](https://modelscale.dev/models/o1-preview) | OpenAI | 76.5 | Observed 2026-11-21 · source benchlm:models |
| 118 | [Qwen3 Max](https://modelscale.dev/models/qwen3-max) | Alibaba | 76.4 | Observed 2026-11-21 · source benchlm:models |
| 119 | [Command A+](https://modelscale.dev/models/command-a-plus) | Cohere | 76.1 | Observed 2026-11-21 · source benchlm:models |
| 120 | [North Mini Code](https://modelscale.dev/models/north-mini-code-1-0) | Cohere | 75.7 | Observed 2026-11-21 · source benchlm:models |
| 121 | [Gemma 4 12B](https://modelscale.dev/models/gemma-4-12b) | Google | 75.3 | Observed 2026-11-21 · source benchlm:models |
| 122 | [Trinity-Large-Preview](https://modelscale.dev/models/trinity-large-preview) | Arcee AI | 75.2 | Observed 2026-11-21 · source benchlm:models |
| 122 | [Trinity-Large-Thinking](https://modelscale.dev/models/trinity-large-thinking) | Arcee AI | 75.2 | Observed 2026-11-21 · source benchlm:models |
| 124 | [DeepSeek V3.2](https://modelscale.dev/models/deepseek-v3-2) | DeepSeek | 75.1 | Observed 2026-11-21 · source benchlm:models |
| 125 | [Mistral Medium 3.5 128B](https://modelscale.dev/models/mistral-medium-3-5-128b) | Mistral | 74.8 | Observed 2026-11-21 · source benchlm:models |
| 125 | [o3-mini](https://modelscale.dev/models/o3-mini) | OpenAI | 74.8 | Observed 2026-11-21 · source benchlm:models |
| 127 | [o1](https://modelscale.dev/models/o1) | OpenAI | 74.7 | Observed 2026-11-21 · source benchlm:models |
| 128 | [Nemotron 3.5 Lightning 30B A3B NVFP4](https://modelscale.dev/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | 74.3 | Observed 2026-11-21 · source benchlm:models |
| 129 | [Sarvam 105B](https://modelscale.dev/models/sarvam-105b) | Sarvam | 73.8 | Observed 2026-11-21 · source benchlm:models |
| 130 | [DeepSeek V3.1](https://modelscale.dev/models/deepseek-v3-1) | DeepSeek | 73.5 | Observed 2026-11-21 · source benchlm:models |
| 131 | [Ling 3.0 Tiny](https://modelscale.dev/models/ling-3-0-tiny) | InclusionAI | 73.4 | Observed 2026-11-21 · source benchlm:models |
| 132 | [GLM-4.5-Air](https://modelscale.dev/models/glm-4-5-air) | Z.AI | 73.3 | Observed 2026-11-21 · source benchlm:models |
| 133 | [Quasar 438B](https://modelscale.dev/models/quasar-438b) | Multiverse Computing | 73.2 | Observed 2026-11-21 · source benchlm:models |
| 134 | [Nemotron Ultra 253B](https://modelscale.dev/models/nemotron-ultra-253b) | NVIDIA | 72.8 | Observed 2026-11-21 · source benchlm:models |
| 135 | [Grok Code Fast 1](https://modelscale.dev/models/grok-code-fast-1) | xAI | 72.7 | Observed 2026-11-21 · source benchlm:models |
| 136 | [Qwen3-Omni-30B-A3B-Thinking](https://modelscale.dev/models/qwen3-omni-30b-a3b-thinking) | Alibaba | 72.6 | Observed 2026-11-21 · source benchlm:models |
| 137 | [Solar Pro 3](https://modelscale.dev/models/solar-pro-3) | Upstage | 72.4 | Observed 2026-11-21 · source benchlm:models |
| 138 | [MiniCPM5-2B](https://modelscale.dev/models/minicpm5-2b) | OpenBMB | 70.2 | Observed 2026-11-21 · source benchlm:models |
| 139 | [Claude 4 Opus](https://modelscale.dev/models/claude-4-opus) | Anthropic | 70.1 | Observed 2026-11-21 · source benchlm:models |
| 140 | [GPT-OSS 20B](https://modelscale.dev/models/gpt-oss-20b) | OpenAI | 68.8 | Observed 2026-11-21 · source benchlm:models |
| 141 | [Claude 4 Sonnet](https://modelscale.dev/models/claude-4-sonnet) | Anthropic | 68.3 | Observed 2026-11-21 · source benchlm:models |
| 141 | [Gemini 2.5 Flash](https://modelscale.dev/models/gemini-2-5-flash) | Google | 68.3 | Observed 2026-11-21 · source benchlm:models |
| 143 | [Mistral Large 3](https://modelscale.dev/models/mistral-large-3) | Mistral | 68.0 | Observed 2026-11-21 · source benchlm:models |
| 144 | [Magistral Medium](https://modelscale.dev/models/magistral-medium) | Mistral | 67.9 | Observed 2026-11-21 · source benchlm:models |
| 145 | [Llama 4 Maverick](https://modelscale.dev/models/llama-4-maverick) | Meta | 67.1 | Observed 2026-11-21 · source benchlm:models |
| 146 | [GPT-4.1](https://modelscale.dev/models/gpt-4-1) | OpenAI | 66.6 | Observed 2026-11-21 · source benchlm:models |
| 147 | [GPT-4.1 mini](https://modelscale.dev/models/gpt-4-1-mini) | OpenAI | 66.4 | Observed 2026-11-21 · source benchlm:models |
| 148 | [Claude 3.7 Sonnet](https://modelscale.dev/models/claude-3-7-sonnet) | Anthropic | 65.6 | Observed 2026-11-21 · source benchlm:models |
| 148 | [MiMo-V2-Flash](https://modelscale.dev/models/mimo-v2-flash) | Xiaomi | 65.6 | Observed 2026-11-21 · source benchlm:models |
| 150 | [DeepSeek V3 0324](https://modelscale.dev/models/deepseek-v3-0324) | DeepSeek | 65.5 | Observed 2026-11-21 · source benchlm:models |
| 151 | [Granite 4.2 30B](https://modelscale.dev/models/granite-4-2-30b) | IBM | 64.4 | Observed 2026-11-21 · source benchlm:models |
| 152 | [Magistral Small](https://modelscale.dev/models/magistral-small) | Mistral | 64.1 | Observed 2026-11-21 · source benchlm:models |
| 153 | [Grok 4.1 Fast](https://modelscale.dev/models/grok-4-1-fast) | xAI | 63.7 | Observed 2026-11-21 · source benchlm:models |
| 154 | [Sarvam 30B](https://modelscale.dev/models/sarvam-30b) | Sarvam | 63.3 | Observed 2026-11-21 · source benchlm:models |
| 155 | [GLM-4.6](https://modelscale.dev/models/glm-4-6) | Z.AI | 63.2 | Observed 2026-11-21 · source benchlm:models |
| 156 | [Celeris-1](https://modelscale.dev/models/celeris-1) | Celeris | 63.1 | Observed 2026-11-21 · source benchlm:models |
| 156 | [Granite 4.2 8B](https://modelscale.dev/models/granite-4-2-8b) | IBM | 63.1 | Observed 2026-11-21 · source benchlm:models |
| 158 | [Exaone 4.0 32B](https://modelscale.dev/models/exaone-4-0-32b) | LG AI Research | 62.8 | Observed 2026-11-21 · source benchlm:models |
| 159 | [Gemini 2.0 Flash](https://modelscale.dev/models/gemini-2-0-flash) | Google | 62.3 | Observed 2026-11-21 · source benchlm:models |
| 160 | [Qwen3-Omni-30B-A3B-Instruct](https://modelscale.dev/models/qwen3-omni-30b-a3b-instruct) | Alibaba | 62.0 | Observed 2026-11-21 · source benchlm:models |
| 161 | [DeepSeek R1 Distill Qwen 32B](https://modelscale.dev/models/deepseek-r1-distill-qwen-32b) | DeepSeek | 61.5 | Observed 2026-11-21 · source benchlm:models |
| 162 | [o1-mini](https://modelscale.dev/models/o1-mini) | OpenAI | 60.3 | Observed 2026-11-21 · source benchlm:models |
| 163 | [Ling 2.6 Flash](https://modelscale.dev/models/ling-2-6-flash) | InclusionAI | 59.3 | Observed 2026-11-21 · source benchlm:models |
| 163 | [QwQ-32B](https://modelscale.dev/models/qwq-32b) | Alibaba | 59.3 | Observed 2026-11-21 · source benchlm:models |
| 165 | [Gemini 1.5 Pro](https://modelscale.dev/models/gemini-1-5-pro) | Google | 58.9 | Observed 2026-11-21 · source benchlm:models |
| 166 | [Llama 4 Scout](https://modelscale.dev/models/llama-4-scout) | Meta | 58.7 | Observed 2026-11-21 · source benchlm:models |
| 167 | [Mistral Medium 3](https://modelscale.dev/models/mistral-medium-3) | Mistral | 57.8 | Observed 2026-11-21 · source benchlm:models |
| 168 | [Gemma 4 E4B](https://modelscale.dev/models/gemma-4-e4b) | Google | 57.6 | Observed 2026-11-21 · source benchlm:models |
| 169 | [Phi-4](https://modelscale.dev/models/phi-4) | Microsoft | 57.5 | Observed 2026-11-21 · source benchlm:models |
| 169 | [Phi-4-reasoning](https://modelscale.dev/models/phi-4-reasoning) | Microsoft | 57.5 | Observed 2026-11-21 · source benchlm:models |
| 171 | [Solar Pro 2](https://modelscale.dev/models/solar-pro-2) | Upstage | 56.1 | Observed 2026-11-21 · source benchlm:models |
| 172 | [Granite 4.2 3B](https://modelscale.dev/models/granite-4-2-3b) | IBM | 55.9 | Observed 2026-11-21 · source benchlm:models |
| 173 | [LFM2.5-2.6B](https://modelscale.dev/models/lfm2-5-2-6b) | LiquidAI | 55.8 | Observed 2026-11-21 · source benchlm:models |
| 174 | [DeepSeek V3](https://modelscale.dev/models/deepseek-v3) | DeepSeek | 55.7 | Observed 2026-11-21 · source benchlm:models |
| 175 | [GPT-4o](https://modelscale.dev/models/gpt-4o) | OpenAI | 54.3 | Observed 2026-11-21 · source benchlm:models |
| 176 | [Llama 3.1 405B](https://modelscale.dev/models/llama-3-1-405b) | Meta | 51.5 | Observed 2026-11-21 · source benchlm:models |
| 177 | [LFM2.5-8B-A1B](https://modelscale.dev/models/lfm2-5-8b-a1b) | LiquidAI | 51.3 | Observed 2026-11-21 · source benchlm:models |
| 178 | [GPT-4.1 nano](https://modelscale.dev/models/gpt-4-1-nano) | OpenAI | 51.2 | Observed 2026-11-21 · source benchlm:models |
| 179 | [Nova Pro](https://modelscale.dev/models/nova-pro) | Amazon | 49.9 | Observed 2026-11-21 · source benchlm:models |
| 180 | [Llama 3.3 70B](https://modelscale.dev/models/llama-3-3-70b) | Meta | 49.8 | Observed 2026-11-21 · source benchlm:models |
| 180 | [Ultravox v0.6 Llama 3.3 70B](https://modelscale.dev/models/ultravox-v0-6-llama-3-3-70b) | Fixie AI | 49.8 | Observed 2026-11-21 · source benchlm:models |
| 182 | [Llama 3.1 70B](https://modelscale.dev/models/llama-3-1-70b) | Meta | 49.1 | Observed 2026-11-21 · source benchlm:models |
| 183 | [Claude 3 Opus](https://modelscale.dev/models/claude-3-opus) | Anthropic | 48.9 | Observed 2026-11-21 · source benchlm:models |
| 184 | [Mistral Large 2](https://modelscale.dev/models/mistral-large-2) | Mistral | 48.6 | Observed 2026-11-21 · source benchlm:models |
| 185 | [Gemini 2.5 Flash-Lite](https://modelscale.dev/models/gemini-2-5-flash-lite) | Google | 47.4 | Observed 2026-11-21 · source benchlm:models |
| 186 | [Nemotron 3 Nano Omni 30B A3B](https://modelscale.dev/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 46.9 | Observed 2026-11-21 · source benchlm:models |
| 187 | [Gemini 1.5 Flash](https://modelscale.dev/models/gemini-1-5-flash) | Google | 46.3 | Observed 2026-11-21 · source benchlm:models |
| 188 | [Mistral Small 3.1](https://modelscale.dev/models/mistral-small-3-1) | Mistral | 45.4 | Observed 2026-11-21 · source benchlm:models |
| 189 | [Gemma 4 E2B](https://modelscale.dev/models/gemma-4-e2b) | Google | 43.3 | Observed 2026-11-21 · source benchlm:models |
| 190 | [Gemma 3 27B](https://modelscale.dev/models/gemma-3-27b) | Google | 42.8 | Observed 2026-11-21 · source benchlm:models |
| 191 | [GPT-4o mini](https://modelscale.dev/models/gpt-4o-mini) | OpenAI | 42.6 | Observed 2026-11-21 · source benchlm:models |
| 192 | [Exaone 4.0 1.2B](https://modelscale.dev/models/exaone-4-0-1-2b) | LG AI Research | 42.4 | Observed 2026-11-21 · source benchlm:models |
| 193 | [DeepSeek-V2.5](https://modelscale.dev/models/deepseek-v2-5) | DeepSeek | 42.3 | Observed 2026-11-21 · source benchlm:models |
| 194 | [Qwen2.5 Coder 32B Instruct](https://modelscale.dev/models/qwen2-5-coder-32b-instruct) | Alibaba | 41.7 | Observed 2026-11-21 · source benchlm:models |
| 195 | [Devstral Small](https://modelscale.dev/models/devstral-small) | Mistral | 41.4 | Observed 2026-11-21 · source benchlm:models |
| 196 | [Claude 3.5 Haiku](https://modelscale.dev/models/claude-3-5-haiku) | Anthropic | 40.8 | Observed 2026-11-21 · source benchlm:models |
| 197 | [Nemotron 3 Nano 30B](https://modelscale.dev/models/nemotron-3-nano-30b) | NVIDIA | 39.9 | Observed 2026-11-21 · source benchlm:models |
| 198 | [Claude 3 Haiku](https://modelscale.dev/models/claude-3-haiku) | Anthropic | 37.4 | Observed 2026-11-21 · source benchlm:models |
| 199 | [Phi-4 Multimodal Instruct](https://modelscale.dev/models/phi-4-multimodal-instruct) | Microsoft | 31.5 | Observed 2026-11-21 · source benchlm:models |
| 200 | [LFM2.5-VL-1.6B-Extract](https://modelscale.dev/models/lfm2-5-vl-1-6b-extract) | LiquidAI | 28.9 | Observed 2026-11-21 · source benchlm:models |
| 201 | [Granite-4.0-1B](https://modelscale.dev/models/granite-4-0-1b) | IBM | 28.1 | Last good 2026-09-18 · source benchlm:models |
| 202 | [Gemini 1.0 Pro](https://modelscale.dev/models/gemini-1-0-pro) | Google | 27.7 | Observed 2026-11-21 · source benchlm:models |
| 203 | [Llama 3.1 8B](https://modelscale.dev/models/llama-3-1-8b) | Meta | 27.0 | Observed 2026-11-21 · source benchlm:models |
| 204 | [Granite-4.0-H-1B](https://modelscale.dev/models/granite-4-0-h-1b) | IBM | 26.3 | Observed 2026-11-21 · source benchlm:models |
| 205 | [Granite-4.0-350M](https://modelscale.dev/models/granite-4-0-350m) | IBM | 26.1 | Observed 2026-11-21 · source benchlm:models |
| 206 | [Granite-4.0-H-350M](https://modelscale.dev/models/granite-4-0-h-350m) | IBM | 25.7 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
