AlgoWorlds - Reference Utility: leaderboard

Metric: Reference utility (%; x100 of a 0-1 score per feasible decision, 1 at the global optimum and 0 at a predefined suboptimal reference decision, 0 when infeasible; 240 partially observed environments built from ten combinatorial optimization families at four workload levels; the agent sees a hidden instance only through task-specific information tools, then commits one structured decision checked by an independent verifier; every model at its maximum reasoning setting; mean of three trials). Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol (Max)74.98
2Claude Opus 4.8 (Max)73.14
3Claude Sonnet 5 (Max)67.2
4GPT-5.6 Terra (Max)54.1
5GLM-5.2 (Max)35.48
6Qwen 3.5 Plus15.82

Interactive version: theaggregate.ai/benchmark?slug=algoworlds-reference-utility · How It Works · Data refreshed daily, snapshot 2026-09-26.