Gamow LabRobotBench v0.1: leaderboard

LabRobotBench v0.1 — Recovery of robotic laboratory workflows across3tasks,one attempt per configuration. Mean dense recovery score includes inherited work and uses a retrospectively chosen rubric;all six systems pass0/3strict tasks. Source-native provider/harness/runtime differences remain explicit;score fraction0–1.

Metric: Mean dense recovery score (fraction, 0–1). Source: gamowlabs.com. Saturation forecast: Around 2031. 6 models tracked. Updated 15 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6.1 Sol0.467#10
2Gemini 4 HydrogenGamow run: native=vanilla_gemini__gemini-4-hydrogen-eap, access=EAP0.3169#11
3Claude Opus 5.50.2299#5
4Claude Fable 5.20.2116#1
5Gemini 4 Argon0.2087#12
6Gemini 4 Carbon0.2072#2

No result here: #6 GPT-6 Astra.

Interactive version: theaggregate.ai/benchmark?slug=gamow-labrobotbench-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-16.