Athene-V2-Chat — benchmark results

Provider: Other. Access: Open.

Unified ELO 1496 ± 26, rank #802 of 1726 rated models, from 15 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
BRIDGE Medical Leaderboard43.9Average Performance (%)90.6
BRIDGE Medical Leaderboard - Zero-Shot41.69Average Performance (%)90.6
BRIDGE Medical Leaderboard - Few-Shot50.68Average Performance (%)89.2
BigCodeBench47.2Pass@1 (%)88.9
BRIDGE Medical Leaderboard - CoT39.34Average Performance (%)88.7
U-MATH - Precalculus85Accuracy (%)72.7
U-MATH - Integral Calculus31.25Accuracy (%)69.7
U-MATH - Multivariable Calculus55.62Accuracy (%)69.7
U-MATH54.91Accuracy (%)66.7
U-MATH - Differential Calculus36.82Accuracy (%)66.7
U-MATH - Sequences & Series57.79Accuracy (%)66.7
U-MATH - Algebra74.44Accuracy (%)47

Interactive version: aibenchmarks.dev/model?slug=athene-v2-chat · How the rankings work · Data refreshed daily, snapshot 2026-07-08.