QuestBench: leaderboard
As AI becomes part of everyday learning, many courses teach students to use it mainly as a productivity tool: how to prompt, search, summarize, write, code, and use tools more efficiently. We argue that AI education also needs a setting in which students learn to test AI and understand their own role in judging machine-produced knowledge. To this end, we introduce a course-based practice that teac
Metric: Pass Rate (%) (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 57.58 | #31 |
| 2 | Claude Opus 4.7 | 52.94 | #49 |
| 3 | GLM-5.1 | 35.14 | #97 |
| 4 | DeepSeek V4 Pro | 32.43 | #102 |
| 5 | Kimi K2.6 | 32.26 | #104 |
| 6 | Gemini 3.1 Pro (Preview) | 31.82 | #58 |
| 7 | Qwen 3.6 Plus | 30.95 | #120 |
| 8 | Kimi K2.5 | 25.26 | #144 |
| 9 | MiMo-V2.5-Pro | 22.73 | #158 |
| 10 | MiniMax-M2.7 | 16.67 | #258 |
| 11 | DeepSeek V3.2 | 7.81 | #205 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=questbench · How It Works · Data refreshed daily, snapshot 2026-10-20.