OWE-Bench - Overall: leaderboard

OWE-Bench - Overall — 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 5.2Max0.5457#1
2GPT-6 AstraMax0.442#6
3Claude Opus 5.5Max0.4159#5
4GPT-6.1 SolMax0.4116#10
5Claude Sonnet 5.5Max0.39#19
6Gemini 4 CarbonHigh0.3276#2
7Claude Fable 5.1Max0.2912#15
8Gemini 4 ArgonHigh0.2407#12
9Muse WonderMax0.1274#28
10DeepSeek V4.1 FlashMax0.1237#62
11GLM-5.3Max0.1184#68
12Grok 4.7xHigh0.07026#47
13Beam 1.0Max0.03338#206
14InklingMax0.01123#281

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