OWE-Bench - Spectral Kinetics Forecast: leaderboard

OWE-Bench - Spectral Kinetics Forecast — 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 February 2027. 14 models tracked. Updated 15 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6 AstraMax0.8148#6
2Claude Fable 5.2Max0.775#1
3Claude Sonnet 5.5Max0.7744#19
4GPT-6.1 SolMax0.6138#10
5Claude Opus 5.5Max0.5278#5
6Gemini 4 ArgonHigh0.3659#12
7Claude Fable 5.1Max0.3504#15
8Gemini 4 CarbonHigh0.2832#2
9Muse WonderMax0.2804#28
10GLM-5.3Max0.154#68
11Grok 4.7xHigh0.1327#47
12DeepSeek V4.1 FlashMax0.0963#62
13Beam 1.0Max0.04553#206
14InklingMax0.01705#281

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