OWE-Bench - ML: leaderboard

OWE-Bench - ML — Expert-built long-horizon science, software, ML and engineering tasks with task-specific hardware and4–18hour budgets; native baseline/ceiling normalized held-out reward,mean of8attempts and equal task means. Web frozen October1,2026;deterministic sealed verifier. Native model/effort and every attempt retained. Score fraction0–1;higher is better.

Metric: Mean normalized held-out task score (fraction, 0–1). Source: openworldengineer.mercor.com. Saturation forecast: Around September 2027. 14 models tracked. Updated 15 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Fable 5.2Max0.5456#1
2Claude Sonnet 5.5Max0.4778#19
3Claude Opus 5.5Max0.4258#5
4GPT-6.1 SolMax0.3935#10
5GPT-6 AstraMax0.3894#6
6Gemini 4 CarbonHigh0.3639#2
7Gemini 4 ArgonHigh0.3215#12
8Claude Fable 5.1Max0.3187#15
9DeepSeek V4.1 FlashMax0.1679#62
10GLM-5.3Max0.1571#68
11Muse WonderMax0.1194#28
12Grok 4.7xHigh0.06599#47
13Beam 1.0Max0.02765#206
14InklingMax0.007109#281

Interactive version: theaggregate.ai/benchmark?slug=owe-bench-ml · How It Works · Data refreshed daily, snapshot 2026-11-16.