SuperGPQA — leaderboard
Graduate-level QA benchmark spanning 285 disciplines. 10,000+ questions at graduate-level difficulty from verified experts. Tests deep, specialized knowledge beyond typical benchmarks.
Metric: Accuracy (%). Source: supergpqa.github.io. Status: saturation imminent. 69 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 73.75 |
| 2 | GPT-5.2 Pro | 67.13 |
| 3 | GPT-5.1 (Thinking) | 66.35 |
| 4 | GPT-5 | 65.63 |
| 5 | Gemini 2.5 Pro | 64.51 |
| 6 | Grok 4 | 62.99 |
| 7 | DeepSeek R1 | 61.82 |
| 8 | Claude Opus 4 (20250514) | 61.43 |
| 9 | O1 (2024-12-17) | 60.24 |
| 10 | DeepSeek V3.1 | 59.32 |
| 11 | Gemini 2.5 Flash | 58.91 |
| 12 | GPT-5 Mini | 58.82 |
| 13 | Kimi K2 (0711) | 58.08 |
| 14 | GPT-5 Chat | 57.36 |
| 15 | Claude Sonnet 4 (20250514) | 57.01 |
Interactive version: theaggregate.ai/benchmark?slug=supergpqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.