ORAgentBench - Easy Quality: leaderboard

Metric: Mean normalized objective quality (0-100) on the 32 easy tasks, zero for infeasible submissions and 0.5 at the verified reference solution; end-to-end operations research tasks packaged with multi-file operational data, configuration and a submission schema; the agent writes and runs solver code in an isolated Harbor environment (45-minute interaction budget, 5-minute solve limit) and hidden validators score schema and hard-constraint feasibility and normalized objective quality; printed 0-1 and x100 here; higher is better. Source: arxiv.org. Saturation forecast: Around 2034. 14 models tracked.

Top models

#ModelScore
1Claude Opus 4.649
2DeepSeek V4 Flash45
3Qwen 3.5 Plus45
4GPT-5.4 (High)45
5GPT-5.4 Mini (High)43
6MiMo-V2.5-Pro42
7MiniMax-M2.739
8DeepSeek V4 Pro38
9Qwen 3.6 Plus38
10GLM-5.137
11GLM-535
12Claude Sonnet 4.631
13GPT-5.3 Codex (High)30
14Kimi K2.629

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