OWE-Bench - MicroPython VM Speedup: leaderboard

OWE-Bench - MicroPython VM 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 September 2027. 14 models tracked. Updated 15 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Fable 5.2Max0.5798#1
2Claude Opus 5.5Max0.4888#5
3Claude Sonnet 5.5Max0.4846#19
4Claude Fable 5.1Max0.3376#15
5GPT-6 AstraMax0.3295#6
6GPT-6.1 SolMax0.272#10
7DeepSeek V4.1 FlashMax0.1546#62
8GLM-5.3Max0.1281#68
9Gemini 4 ArgonHigh0.06328#12
10Gemini 4 CarbonHigh0.05785#2
11Muse WonderMax0.05759#28
12Beam 1.0Max0.02039#206
13InklingMax0.01196#281
14Grok 4.7xHigh0.01051#47

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