# GPQA Diamond (Vals) 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-vals-gpqa-diamond

GPQA Diamond, Vals AI run. Every model the catalog carries a published GPQA Diamond (Vals) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Accuracy |
| Tasks | Graduate-level science questions |
| Difficulty | Expert reasoning |
| Published by | [Vals AI GPQA Diamond, Vals AI run leaderboard](https://www.vals.ai/benchmarks/gpqa) |

Vals AI’s independent run of the GPQA Diamond graduate-level science questions.

## GPQA Diamond (Vals) ranking

91 models with a published GPQA Diamond (Vals) 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 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 95.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 95.2 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 94.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 94.4 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 3.7 Flash](https://modelscale.dev/models/gemini-3-7-flash) | Google | 93.9 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 93.7 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 93.4 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 93.4 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Gemini 3.6 Flash](https://modelscale.dev/models/gemini-3-6-flash) | Google | 93.4 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 93.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 93.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Grok 4.5](https://modelscale.dev/models/grok-4-5) | xAI | 92.9 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 92.9 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 92.7 | Observed 2026-11-21 · source benchlm:models |
| 14 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 92.7 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 92.4 | Observed 2026-11-21 · source benchlm:models |
| 16 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | 92.4 | Observed 2026-11-21 · source benchlm:models |
| 16 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 92.4 | Last good 2026-11-18 · source benchlm:models |
| 19 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 91.7 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 91.7 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 91.7 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | 91.7 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | 91.4 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Muse Spark 1.1](https://modelscale.dev/models/muse-spark-1-1) | Meta | 91.2 | Observed 2026-11-21 · source benchlm:models |
| 25 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | 90.9 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 90.2 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 90.2 | Observed 2026-11-21 · source benchlm:models |
| 28 | [DeepSeek V4 Flash 0731](https://modelscale.dev/models/deepseek-v4-flash-max) | DeepSeek | 89.9 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Claude Opus 4.6 (Adaptive)](https://modelscale.dev/models/claude-opus-4-6-thinking) | Anthropic | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Muse Spark](https://modelscale.dev/models/muse-spark) | Meta | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 89.1 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 88.9 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | 88.9 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Grok 4.20](https://modelscale.dev/models/grok-4-20-beta) | xAI | 88.6 | Observed 2026-11-21 · source benchlm:models |
| 35 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 88.1 | Observed 2026-11-21 · source benchlm:models |
| 35 | [Grok 4](https://modelscale.dev/models/grok-4) | xAI | 88.1 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Gemini 3 Flash](https://modelscale.dev/models/gemini-3-flash) | Google | 87.9 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 87.4 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 87.1 | Observed 2026-11-21 · source benchlm:models |
| 40 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 40 | [MiniMax M2.7](https://modelscale.dev/models/minimax-m2-7) | MiniMax | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 42 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | 86.4 | Observed 2026-11-21 · source benchlm:models |
| 43 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 86.1 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Claude Opus 4.5 Thinking](https://modelscale.dev/models/claude-opus-4-5-thinking) | Anthropic | 85.9 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 45 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 45 | [GPT-5](https://modelscale.dev/models/gpt-5) | OpenAI | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 45 | [GPT-5 (high)](https://modelscale.dev/models/gpt-5-high) | OpenAI | 85.6 | Last good 2026-11-18 · source benchlm:models |
| 49 | [Grok 4 Fast (Reasoning)](https://modelscale.dev/models/grok-4-fast-reasoning) | xAI | 85.4 | Observed 2026-11-21 · source benchlm:models |
| 50 | [Ling 3.0 Flash](https://modelscale.dev/models/ling-3-0-flash) | InclusionAI | 84.8 | Observed 2026-11-21 · source benchlm:models |
| 51 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | 84.5 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Grok 4.1 Fast (Reasoning)](https://modelscale.dev/models/grok-4-1-fast-reasoning) | xAI | 84.3 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Kimi K2.5 (Reasoning)](https://modelscale.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 84.1 | Last good 2026-11-18 · source benchlm:models |
| 53 | [o3](https://modelscale.dev/models/o3) | OpenAI | 84.1 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Gemini 3.5 Flash-Lite](https://modelscale.dev/models/gemini-3-5-flash-lite) | Google | 83.8 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | 83.6 | Observed 2026-11-21 · source benchlm:models |
| 57 | [GLM-5 (Reasoning)](https://modelscale.dev/models/glm-5-reasoning) | Z.AI | 83.3 | Last good 2026-11-18 · source benchlm:models |
| 58 | [GPT-5.4 mini](https://modelscale.dev/models/gpt-5-4-mini) | OpenAI | 83.1 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Qwen3.5 Flash](https://modelscale.dev/models/qwen3-5-flash) | Alibaba | 82.8 | Observed 2026-11-21 · source benchlm:models |
| 60 | [MiMo-V2.5-Pro](https://modelscale.dev/models/mimo-v2-5-pro) | Xiaomi | 82.6 | Observed 2026-11-21 · source benchlm:models |
| 61 | [Claude Sonnet 4.5 Thinking](https://modelscale.dev/models/claude-sonnet-4-5-thinking) | Anthropic | 81.6 | Observed 2026-11-21 · source benchlm:models |
| 61 | [MiMo-V2.5](https://modelscale.dev/models/mimo-v2-5) | Xiaomi | 81.6 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Gemini 3.1 Flash-Lite](https://modelscale.dev/models/gemini-3-1-flash-lite) | Google | 81.1 | Observed 2026-11-21 · source benchlm:models |
| 64 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 80.1 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 79.5 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Qwen3 Max](https://modelscale.dev/models/qwen3-max) | Alibaba | 79.5 | Observed 2026-11-21 · source benchlm:models |
| 67 | [GPT-5.4 nano](https://modelscale.dev/models/gpt-5-4-nano) | OpenAI | 77.5 | Observed 2026-11-21 · source benchlm:models |
| 68 | [o3-mini](https://modelscale.dev/models/o3-mini) | OpenAI | 75.5 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Claude 3.7 Sonnet Thinking](https://modelscale.dev/models/claude-3-7-sonnet-thinking) | Anthropic | 75.3 | Observed 2026-11-21 · source benchlm:models |
| 70 | [GLM-4.6](https://modelscale.dev/models/glm-4-6) | Z.AI | 74.5 | Observed 2026-11-21 · source benchlm:models |
| 70 | [o4-mini](https://modelscale.dev/models/o4-mini) | OpenAI | 74.5 | Observed 2026-11-21 · source benchlm:models |
| 70 | [o4-mini (high)](https://modelscale.dev/models/o4-mini-high) | OpenAI | 74.5 | Last good 2026-11-18 · source benchlm:models |
| 73 | [o1](https://modelscale.dev/models/o1) | OpenAI | 73.2 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Claude Haiku 4.5](https://modelscale.dev/models/claude-haiku-4-5) | Anthropic | 72.2 | Observed 2026-11-21 · source benchlm:models |
| 74 | [GLM-4.5](https://modelscale.dev/models/glm-4-5) | Z.AI | 72.2 | Observed 2026-11-21 · source benchlm:models |
| 76 | [Mistral Large 3](https://modelscale.dev/models/mistral-large-3) | Mistral | 68.4 | Observed 2026-11-21 · source benchlm:models |
| 77 | [GPT-4.1 mini](https://modelscale.dev/models/gpt-4-1-mini) | OpenAI | 67.9 | Observed 2026-11-21 · source benchlm:models |
| 78 | [Claude 3.7 Sonnet](https://modelscale.dev/models/claude-3-7-sonnet) | Anthropic | 67.4 | Observed 2026-11-21 · source benchlm:models |
| 79 | [GPT-4.1](https://modelscale.dev/models/gpt-4-1) | OpenAI | 65.4 | Observed 2026-11-21 · source benchlm:models |
| 80 | [Gemini 2.0 Flash](https://modelscale.dev/models/gemini-2-0-flash) | Google | 65.2 | Observed 2026-11-21 · source benchlm:models |
| 81 | [Claude 3.5 Sonnet](https://modelscale.dev/models/claude-3-5-sonnet) | Anthropic | 59.3 | Observed 2026-11-21 · source benchlm:models |
| 81 | [MiMo-V2-Flash](https://modelscale.dev/models/mimo-v2-flash) | Xiaomi | 59.3 | Observed 2026-11-21 · source benchlm:models |
| 83 | [Gemini 1.5 Pro](https://modelscale.dev/models/gemini-1-5-pro) | Google | 58.3 | Observed 2026-11-21 · source benchlm:models |
| 84 | [Laguna XS.2](https://modelscale.dev/models/laguna-xs-2) | Poolside | 55.1 | Observed 2026-11-21 · source benchlm:models |
| 85 | [GPT-4o](https://modelscale.dev/models/gpt-4o) | OpenAI | 53.8 | Observed 2026-11-21 · source benchlm:models |
| 86 | [GPT-4.1 nano](https://modelscale.dev/models/gpt-4-1-nano) | OpenAI | 50.8 | Observed 2026-11-21 · source benchlm:models |
| 87 | [Gemini 1.5 Flash](https://modelscale.dev/models/gemini-1-5-flash) | Google | 46.0 | Observed 2026-11-21 · source benchlm:models |
| 88 | [GPT-4o mini](https://modelscale.dev/models/gpt-4o-mini) | OpenAI | 44.2 | Observed 2026-11-21 · source benchlm:models |
| 89 | [Claude 3.5 Haiku](https://modelscale.dev/models/claude-3-5-haiku) | Anthropic | 37.9 | Observed 2026-11-21 · source benchlm:models |
| 90 | [Mistral Medium 3.5 128B](https://modelscale.dev/models/mistral-medium-3-5-128b) | Mistral | 34.8 | Observed 2026-11-21 · source benchlm:models |
| 91 | [Laguna M.1](https://modelscale.dev/models/laguna-m-1) | Poolside | 27.0 | 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.
