OWE-Bench - Bearing Fault Transfer: leaderboard

OWE-Bench - Bearing Fault Transfer — 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 March 2027. 14 models tracked. Updated 15 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Fable 5.2Max0.6862#1
2Claude Sonnet 5.5Max0.6461#19
3GPT-6 AstraMax0.625#6
4GPT-6.1 SolMax0.5801#10
5Gemini 4 CarbonHigh0.4762#2
6Claude Opus 5.5Max0.4315#5
7Claude Fable 5.1Max0.3378#15
8Gemini 4 ArgonHigh0.3301#12
9Muse WonderMax0.2513#28
10DeepSeek V4.1 FlashMax0.121#62
11Grok 4.7xHigh0.08033#47
12GLM-5.3Max0.07331#68
13Beam 1.0Max0.02709#206
14InklingMax0.01458#281

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