OmniaBench - ToB: leaderboard
Metric: Pass@1 (%; tasks from the business-facing (ToB) 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 June 2027. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 5 (Max) | 60.68 |
| 2 | GPT-5.5 (High) | 58.2 |
| 3 | GPT-5.6 Sol (High) | 57.59 |
| 4 | GLM-5.2 (Max) | 57.28 |
| 5 | Claude Opus 4.7 (Max) | 56.66 |
| 6 | Kimi K2.6 (Thinking) | 54.8 |
| 7 | DeepSeek V4 Pro (Max) | 54.18 |
| 8 | Qwen 3.7 Max (Thinking) | 48.3 |
| 9 | GLM-5 (Thinking) | 47.68 |
| 10 | Gemini 3.5 Flash (High) | 46.75 |
| 11 | DeepSeek V4 Flash (Max) | 45.2 |
| 12 | Qwen 3.5 397B A17B | 44.27 |
| 13 | Qwen 3.6 27B | 43.65 |
| 14 | Gemini 3.1 Pro (Preview) | 42.11 |
| 15 | Qwen 3.6 35B A3B | 41.8 |
Interactive version: theaggregate.ai/benchmark?slug=omniabench-tob · How It Works · Data refreshed daily, snapshot 2026-09-29.