OmniaBench - ToC: leaderboard
Metric: Pass@1 (%; tasks from the consumer-facing (ToC) domain split; a task counts as solved only when every rubric item is satisfied (Program tasks by a VerifyCode check); up to 200 tool-call steps; challenging set of 644 tasks evaluated June 29 to July 15, 2026). Source: arxiv.org. Saturation forecast: Around March 2027. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 5 (Max) | 60.47 |
| 2 | GPT-5.6 Sol (High) | 59.07 |
| 3 | GLM-5.2 (Max) | 55.81 |
| 4 | DeepSeek V4 Pro (Max) | 54.88 |
| 5 | GPT-5.5 (High) | 53.02 |
| 6 | DeepSeek V4 Flash (Max) | 51.63 |
| 7 | Claude Opus 4.7 (Max) | 51.63 |
| 8 | Kimi K2.6 (Thinking) | 49.3 |
| 9 | Qwen 3.7 Max (Thinking) | 48.84 |
| 10 | Gemini 3.5 Flash (High) | 46.98 |
| 11 | Gemini 3.1 Pro (Preview) | 39.53 |
| 12 | Qwen 3.6 27B | 38.6 |
| 13 | GLM-5 (Thinking) | 37.67 |
| 14 | Qwen 3.5 397B A17B | 35.35 |
| 15 | Qwen 3.6 35B A3B | 31.63 |
Interactive version: theaggregate.ai/benchmark?slug=omniabench-toc · How It Works · Data refreshed daily, snapshot 2026-09-29.