OmniaBench - Solver: leaderboard

Metric: Pass@1 (%; 60 selection, scheduling, allocation and optimization tasks synthesized with solver guidance; 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 February 2027. 22 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol (High)65
2Claude Sonnet 5 (Max)56.67
3Qwen 3.7 Max (Thinking)51.67
4Kimi K2.6 (Thinking)45
5Claude Opus 4.7 (Max)43.33
6GPT-5.5 (High)38.33
7Gemini 3.5 Flash (High)36.67
8DeepSeek V4 Pro (Max)36.67
9Gemini 3.1 Pro (Preview)35
10Qwen 3.5 397B A17B31.67
11Qwen 3.6 27B28.33
12DeepSeek V4 Flash (Max)28.33
13GLM-5.2 (Max)26.67
14Qwen 3.5 35B A3B25
15Qwen 3.6 35B A3B20

Interactive version: theaggregate.ai/benchmark?slug=omniabench-solver · How It Works · Data refreshed daily, snapshot 2026-09-29.