BENCHMARK EXPLORER · reasoning
GPQA Diamond
Graduate-level science questions designed to challenge expert reasoning.
What it measures
Accuracy on the Diamond subset of GPQA.
Interpretation caveats
Results depend on prompting and reasoning settings. Published model-card results may be self-reported; do not treat them as independent verification.
Original benchmarkPublished results
| # | Modalities | Compare | ||||
|---|---|---|---|---|---|---|
| 1 | Qwen | InputTextImageVideoOutputText | 262,144tokens | |||
| 2 | moonshotai | InputTextImageOutputText | 262,144tokens | |||
| 3 | Qwen | InputTextImageVideoOutputText | 262,144tokens | |||
| 4 | zai-org | InputTextOutputText | 204,800tokens | |||
| 5 | zai-org | InputTextOutputText | 204,800tokens | |||
| 6 | Qwen | InputTextImageVideoOutputText | 262,144tokens | |||
| 7 | MiniMaxAI | InputTextOutputText | 204,800tokens | |||
| 8 | moonshotai | InputTextOutputText | 262,144tokens | |||
| 9 | Qwen | InputTextImageVideoOutputText | 262,144tokens | |||
| 10 | Nanbeige | InputTextOutputNot documented | —Not documented | |||
| 11 | stepfun-ai | InputTextOutputText | 262,144tokens | |||
| 12 | deepseek-ai | InputTextOutputText | 163,840tokens | |||
| 13 | Qwen | InputTextImageVideoOutputText | 262,144tokens | |||
| 14 | meituan-longcat | InputTextOutputNot documented | —Not documented | |||
| 15 | nvidia | InputTextOutputNot documented | —Not documented | |||
| 16 | LGAI-EXAONE | InputTextOutputNot documented | —Not documented | |||
| 17 | Qwen | InputTextOutputNot documented | —Not documented | |||
| 18 | zai-org | InputTextOutputText | 200,000tokens | |||
| 19 | jdopensource | InputTextOutputNot documented | —Not documented | |||
| 20 | deepseek-ai | InputTextOutputText | 64,000tokens | |||
| 21 | openai | InputTextOutputText | 131,072tokens | |||
| 22 | Qwen | InputTextOutputNot documented | —Not documented | |||
| 23 | Qwen | InputTextOutputNot documented | —Not documented | |||
| 24 | openai | InputTextOutputText | 131,072tokens | |||
| 25 | LiquidAI | InputTextOutputNot documented | —Not documented | |||
| 26 | meta-llama | InputTextOutputText | 131,072tokens | |||
| 27 | Qwen | InputTextOutputNot documented | —Not documented | |||
| — | openbmb | — | InputTextOutputNot documented | —Not documented | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | Anthropic | — | InputTextImageFileOutputText | 1,000,000tokens | ||
| — | nvidia | — | InputTextOutputImage | —Not documented | ||
| — | nvidia | — | InputTextOutputImage | —Not documented | ||
| — | deepseek-ai | — | InputTextOutputText | 163,840tokens | ||
| — | deepseek-ai | — | InputTextOutputText | 163,840tokens | ||
| — | deepseek-ai | — | InputTextOutputText | 163,840tokens | ||
| — | HelpingAI | — | InputTextOutputNot documented | —Not documented | ||
| — | tiiuae | — | InputTextOutputNot documented | —Not documented | ||
| — | — | InputTextOutputText | —Not documented | |||
| — | — | InputAudioFileImageTextVideoOutputText | 1,048,576tokens | |||
| — | — | InputTextImageVideoFileAudioOutputText | 1,048,576tokens | |||
| — | — | InputTextImageVideoFileAudioOutputText | 1,048,576tokens | |||
| — | — | InputAudioFileImageTextVideoOutputText | 1,048,576tokens | |||
| — | thinky | — | InputTextImageAudioOutputText | 524,288tokens |