OWE-Bench - Streaming Payments ETL: leaderboard

OWE-Bench - Streaming Payments ETL — 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
1Claude Fable 5.2Max0.8385#1
2GPT-6.1 SolMax0.5506#10
3Claude Opus 5.5Max0.5385#5
4GPT-6 AstraMax0.5068#6
5Gemini 4 CarbonHigh0.2444#2
6Claude Sonnet 5.5Max0.2089#19
7Gemini 4 ArgonHigh0.1482#12
8Claude Fable 5.1Max0.1333#15
9Muse WonderMax0.007275#28
10DeepSeek V4.1 FlashMax0#62
11GLM-5.3Max0#68
12Grok 4.7xHigh0#47
13InklingMax0#281
14Beam 1.0Max0#206

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