OmniaBench - ToE: leaderboard
Metric: Pass@1 (%; tasks from the employee-oriented (ToE) 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 November 2027. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (High) | 58.49 |
| 2 | GLM-5.2 (Max) | 57.55 |
| 3 | Qwen 3.7 Max (Thinking) | 55.66 |
| 4 | DeepSeek V4 Pro (Max) | 54.72 |
| 5 | DeepSeek V4 Flash (Max) | 52.83 |
| 6 | GPT-5.6 Sol (High) | 51.89 |
| 7 | Claude Opus 4.7 (Max) | 51.89 |
| 8 | Kimi K2.6 (Thinking) | 50.94 |
| 9 | Claude Sonnet 5 (Max) | 48.11 |
| 10 | Qwen 3.6 27B | 44.34 |
| 11 | Qwen 3.5 397B A17B | 43.4 |
| 12 | Gemini 3.1 Pro (Preview) | 42.45 |
| 13 | GLM-5 (Thinking) | 41.51 |
| 14 | Gemini 3.5 Flash (High) | 39.62 |
| 15 | Qwen 3.5 35B A3B | 36.79 |
Interactive version: theaggregate.ai/benchmark?slug=omniabench-toe · How It Works · Data refreshed daily, snapshot 2026-09-29.