SuperGPQA leaderboard
As of November 14, 2026, among the results listed here, Qwen3.6 Plus has the highest reported SuperGPQA score, 71.6, published by Qwen on May 21, 2026, ahead of Qwen3.7 Plus at 71.4. 4 models have a SuperGPQA result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
4 models ranked · 2 makers
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Qwen3.6 Plus | 71.6 | Not published | Qwen | May 21, 2026 |
| 2 | Qwen3.7 Plus | 71.4 | Not published | Qwen | May 21, 2026 |
| 3 | Kimi K2 0711 | 57.2 | Instruction model evaluation results; Acc | Moonshot AI | July 11, 2025 (model release) |
| 4 | Kimi-K2-Base | 44.7 | Base model evaluation results; EM | Moonshot AI | July 11, 2025 (model release) |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- Settings differ between makers. Check the Setting column before comparing two scores.
- Spread
- 71.6 to 44.7 across 4 models.
- Freshness
- Newest result published May 21, 2026; oldest July 11, 2025.
What SuperGPQA measures
SuperGPQA evaluates graduate-level knowledge and reasoning across 285 disciplines; the search results do not specify what its numerical score means. Source: Scaling LLM Evaluation across 285 Graduate Disciplines