ORAgentBench - Medium Quality: leaderboard

Metric: Mean normalized objective quality (0-100) on the 41 medium 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 October 2027. 14 models tracked.

Top models

#ModelScore
1GPT-5.3 Codex (High)37
2Claude Opus 4.632
3GPT-5.4 (High)31
4GLM-5.129
5DeepSeek V4 Pro25
6Kimi K2.625
7GPT-5.4 Mini (High)24
8Claude Sonnet 4.623
9DeepSeek V4 Flash21
10Qwen 3.6 Plus21
11GLM-521
12MiMo-V2.5-Pro20
13Qwen 3.5 Plus13
14MiniMax-M2.73

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