TOBench — leaderboard
Metric: Avg. (self-reported). Source: benchmarklist.com. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 Plus (2026-04-20) | 41 |
| 2 | Qwen 3.6 Plus | 32 |
| 3 | Claude Opus 4.6 | 32 |
| 4 | Gemini 3.1 Pro (Preview) | 30 |
| 5 | Claude Haiku 4.5 | 27 |
| 6 | GPT-5 | 26.8 |
| 7 | Claude Sonnet 4.6 | 23 |
| 8 | GPT-5.2 | 22 |
| 9 | GLM-4.6V | 14 |
| 10 | Gemma 4 31B | 9 |
| 11 | MiniMax-M2.5 | 7 |
| 12 | GPT-4o | 6.12 |
Interactive version: theaggregate.ai/benchmark?slug=tobench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.