JOR-Bench - OptMATH: leaderboard

Metric: Accuracy (%; OptMATH combinatorial and mixed-integer problems, Japanese translation with human post-editing; the model writes a standalone Python program in a fenced block, run with OR-Tools available (300-second and 32 GB limits), correct when the printed value matches the reference within 1e-6; higher is better). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.

Top models

#ModelScore
1GPT-OSS-120B71.7
2Qwen3-Swallow-32B-RL-v0.245.1
3Qwen 3 32B19.5
4Qwen 3 8B13.3
5Qwen3-Swallow-8B-RL-v0.27.2
6NVIDIA-Nemotron-Nano-9B-v2-Japanese1.2

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