GPQA Diamond (BenchmarkList): leaderboard
GPQA Diamond evaluates models on graduate-level science questions in biology, chemistry, and physics using text input. The pinned metric is Accuracy (%), measuring the share of questions answered correctly in the source table. Source: BenchmarkList’s attributed result table.
Metric: Accuracy (%). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Max) | 96.1 | #6 (GPT-6 Astra) |
| 2 | Kimi K3.1 Pro (Max) | 94.2 | #17 (Kimi K3.1 Pro) |
| 3 | Claude Opus 5.5 (Max) | 93.9 | #3 (Claude Opus 5.5) |
| 4 | Claude Fable 5.1 (Max) | 93.7 | #10 (Claude Fable 5.1) |
| 5 | DeepSeek V4.1 Flash (1017) (Max) | 92.2 | #27 (DeepSeek V4.1 Flash (1017)) |
| 6 | GLM-5.3 (Max) | 91.7 | #44 (GLM-5.3) |
No result here: #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=gpqa-diamond-benchmarklist · How It Works · Data refreshed daily, snapshot 2026-11-05.