Every AI leaderboard

28 leaderboards · 986 models ranked

GPQA Diamond (Epoch AI runs) leaderboard: who is #1

Epoch AI · Accuracy, higher is better · 100 models · published Nov 6, 2026

Epoch AI

Top 25 of 100 models, best variant per model as published

#ModelScoreCorrect
1Gemini 4 Argonas “gemini-4-argon_high”96.4%
2GPT-6 Astraas “gpt-6-astra_max”95.8%
3Claude Sonnet 5.5as “claude-sonnet-5-5_max”95.6%
4Gemini 3.8 Flashas “gemini-3.8-flash_high”95.4%
4GPT-6.1 Solas “gpt-6.1-sol_max”95.4%
6Gemini 3.7 Flashas “gemini-3.7-flash_high”94.8%
7GPT-5.4 Proas “gpt-5.4-pro-2026-03-05_xhigh”94.6%
8Gemini 3.1 Pro Previewas “gemini-3.1-pro-preview_high”94.4%
9New, entered at #9 since Oct 28, 2026GPT-6.1 Terraas “gpt-6.1-terra_max”94.3%
9GPT-6 Solas “gpt-6-sol_max”94.3%
11New, entered at #11 since Nov 7, 2026Kimi K3.1 Pro Togetheras “kimi-k3.1-pro-together_max”94.2%
121down from #11 since Nov 7, 2026Gemini 3.6 Flashas “gemini-3.6-flash_high”94.1%
131down from #12 since Nov 7, 2026GPT-5.5 Pre Releaseas “gpt-5.5-pre-release_xhigh”94.0%
131down from #12 since Nov 7, 2026Grok 4.6as “grok-4.6_high”94.0%
151down from #14 since Nov 7, 2026GPT-5.5 Pro Pre Releaseas “gpt-5.5-pro-pre-release_xhigh”93.9%
161down from #15 since Nov 7, 2026Claude Opus 5as “claude-opus-5_max”93.9%
171down from #16 since Nov 7, 2026GPT-5.6 Solas “gpt-5.6-sol_max”93.5%
181down from #17 since Nov 7, 2026Grok 4.5as “grok-4.5_high”93.4%
191down from #18 since Nov 7, 2026GPT-5.6 Terraas “gpt-5.6-terra_max”93.3%
201down from #19 since Nov 7, 2026GPT-5.4as “gpt-5.4-2026-03-05_xhigh”93.3%
211down from #20 since Nov 7, 2026DeepSeek V4.1 Flashas “deepseek-v4.1-flash-1017_max”93.2%
221down from #21 since Nov 7, 2026Doubao Seed Evolvingas “doubao-seed-evolving_high”93.1%
221down from #21 since Nov 7, 2026Kimi K3as “kimi-k3_max”93.1%
241down from #23 since Nov 7, 2026Gemini 3.5 Flashas “gemini-3.5-flash_high”92.8%
251down from #24 since Nov 7, 2026Grok 4.7as “grok-4.7_xhigh”92.7%
About this board and its history

What it measures

198 graduate-level biology, physics and chemistry questions that non-experts cannot look up. Run by Epoch AI.

Rank at each month's end

12345678910SepOctNow1Gemini 4 Argon2GPT-6 Astra3Claude Sonnet 5.54Gemini 3.8 Flash4GPT-6.1 Sol6Gemini 3.7 Flash

Source

Scores as published by Epoch AI on the capture date (2026-11-09). Source: epoch.ai benchmark data (CC BY).

epoch.ai/benchmarks/gpqa-diamond