ORAgentBench - Medium: leaderboard
Metric: Pass rate (%) on the 41 medium tasks: a task passes when the submission is feasible and its normalized quality reaches 0.4; 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; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.3 Codex (High) | 43.9 |
| 2 | Claude Opus 4.6 | 39.02 |
| 3 | GPT-5.4 (High) | 39.02 |
| 4 | Kimi K2.6 | 36.59 |
| 5 | GLM-5.1 | 31.71 |
| 6 | Claude Sonnet 4.6 | 29.27 |
| 7 | GPT-5.4 Mini (High) | 29.27 |
| 8 | DeepSeek V4 Pro | 28.46 |
| 9 | DeepSeek V4 Flash | 26.83 |
| 10 | GLM-5 | 24.39 |
| 11 | Qwen 3.6 Plus | 21.95 |
| 12 | MiMo-V2.5-Pro | 21.95 |
| 13 | Qwen 3.5 Plus | 14.63 |
| 14 | MiniMax-M2.7 | 2.44 |
Interactive version: theaggregate.ai/benchmark?slug=oragentbench-medium · How It Works · Data refreshed daily, snapshot 2026-09-29.