OpenThinker3-7B: benchmark results

Provider: Other.

Aggregate Rating 1332 ± 51, rank #8126 of 10916 rated models, from 5 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open-R1 Eval Leaderboard57.6Average Accuracy (%)69.4
BRIDGE Medical Leaderboard - CoT18.37Average Performance (%)11.7
BRIDGE Medical Leaderboard - Zero-Shot19.79Average Performance (%)8.1
ReasonScape R12225.37ReasonScore0.8
BRIDGE Medical Leaderboard - Few-Shot13.01Average Performance (%)0

Interactive version: theaggregate.ai/model?slug=openthinker3-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.