OWE-Bench - SPARQL Store Speedup: leaderboard

OWE-Bench - SPARQL Store Speedup — 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 5.2Max0.9388#1
2Claude Sonnet 5.5Max0.8322#19
3Claude Opus 5.5Max0.7269#5
4Claude Fable 5.1Max0.5599#15
5Gemini 4 CarbonHigh0.5201#2
6GPT-6.1 SolMax0.3607#10
7GPT-6 AstraMax0.3065#6
8GLM-5.3Max0.1838#68
9Muse WonderMax0.1591#28
10Gemini 4 ArgonHigh0.147#12
11DeepSeek V4.1 FlashMax0.1457#62
12Grok 4.7xHigh0.03846#47
13Beam 1.0Max0.01789#206
14InklingMax0.01309#281

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