Benchmark Leaderboard
Top models by Google-Proof Q&A score
Sorts are only valid inside this benchmark. A score gap of this benchmark does not map to the same gap on another benchmark, so validate any short-list by checking peer rows and model context/price fit.
| # | Model | Score | Version | Source |
|---|---|---|---|---|
| 1 | Gemini 4 Argon | 96.4 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 2 | GPT-6 Astra | 95.8 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 3 | Claude Sonnet 5.5 | 95.6 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 4 | Gemini 3.8 Flash | 95.4 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 5 | GPT-6.1 Sol | 95.4 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 6 | Gemini 3.7 Flash | 94.8 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 7 | Claude Mythos Preview | 94.6 | diamond | https://epoch.ai/benchmarks/gpqa-diamond; https://intuitionlabs.ai/articles/gpqa-diamond-ai-benchmark |
| 8 | GPT-5.6 Sol | 94.6 | GPQA Diamond; max reasoning | https://openai.com/index/gpt-5-6/ |
| 9 | Gemini 3.1 Pro Preview | 94.3 | diamond | https://artificialanalysis.ai/leaderboards/models |
| 10 | GPT-6 Sol | 94.3 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 11 | Claude Opus 4.7 | 94.2 | diamond | https://www.anthropic.com/news/claude-opus-4-7 |
| 12 | Gemini 3.6 Flash | 94.1 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 13 | Grok 4.6 | 94 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 14 | GPT-5.5 | 93.6 | diamond | https://openai.com/index/introducing-gpt-5-5/ |
| 15 | GPT-5.5 Pro | 93.6 | GPQA Diamond | https://codingfleet.com/blog/claude-opus-4-8-vs-gpt-5-5-comparison/ |
| 16 | Claude Opus 4.8 | 93.6 | GPQA Diamond | https://www.anthropic.com/news/claude-opus-4-8 |
| 17 | Kimi K3 | 93.5 | GPQA-Diamond; max reasoning effort | https://www.kimi.com/blog/kimi-k3 |
| 18 | MiniMax M3 | 92.9 | MiniMax M3 GPQA 92 (accuracy%) | https://venturebeat.com/technology/minimax-m3-debuts-eclipsing-gpt-5-5-and-gemini-3-1-pro-on-key-benchmark-performance-for-just-5-10-of-the-cost |
| 19 | Grok 4.7 | 92.7 | diamond | https://epoch.ai/benchmarks/gpqa-diamond |
| 20 | Qwen3.8-Max | 92.6 | GPQA Diamond | https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B |
Interpretation
Trust when:
- Use top rows for shortlisting, then validate provider coverage and feature fit before selecting a model.
- Cross-benchmark consistency is a stronger signal than one-off score dominance.
Don't trust when:
- Don't compare raw score gaps across different benchmark scales as equivalent.
- Missing rows in the heatmap can hide benchmark blind spots.
- No trend data means this is a snapshot; expect drift in fresh refresh cycles.
Cross-benchmark heatmap
Compare top models across selected benchmark families to spot strengths and weak spots. On narrow screens, scroll horizontally to inspect every benchmark.
| Model | GPQA | HellaSwag | HumanEval | MMLU |
|---|---|---|---|---|
| Gemini 4 Argon | 96.4 | — | — | — |
| GPT-6 Astra | 95.8 | — | — | — |
| Claude Sonnet 5.5 | 95.6 | — | — | — |
| Gemini 3.8 Flash | 95.4 | — | — | — |
| GPT-6.1 Sol | 95.4 | — | — | — |
| Gemini 3.7 Flash | 94.8 | — | — | — |