OWE-Bench - Stateful Parquet Lakehouse: leaderboard

OWE-Bench - Stateful Parquet Lakehouse — 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 5.1Max0.497#15
2Gemini 4 CarbonHigh0.4068#2
3Claude Opus 5.5Max0.3766#5
4GPT-6 AstraMax0.3175#6
5Claude Fable 5.2Max0.3136#1
6GPT-6.1 SolMax0.2181#10
7DeepSeek V4.1 FlashMax0.03486#62
8Beam 1.0Max0.02784#206
9Grok 4.7xHigh0.02363#47
10InklingMax0.004075#281
11GLM-5.3Max0.003838#68
12Gemini 4 ArgonHigh0#12
13Claude Sonnet 5.5Max0#19
14Muse WonderMax0#28

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