Chocolatine-2-14B-Instruct-v2.0.3: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1570 ± 32, rank #1407 of 10916 rated models, from 60 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Mbpp Pylint Check98.59Score (%)96.5
Open LLM Leaderboard - GPQA37.92Score94.6
Open LLM Leaderboard - MMLU-Pro53.74Score94.6
Open LLM Leaderboard - MuSR47.68Score93.7
Open LLM Leaderboard - BBH65.48Score92.8
Open LLM Leaderboard - MATH Level 542.07Score91.6
Open Japanese LLM - Xlsum JA Bert Score JA F170.71Score (%)89.8
French LLM Leaderboard - IFEval FR64.32Score (%)88.9
Open Japanese LLM - CG60.44Score (%)87.9
Open Japanese LLM - Xlsum JA RougeLsum26.33Score (%)86.7
Open Japanese LLM - SUM11.32Score (%)86.1
Open Japanese LLM - Xlsum JA Rouge211.33Score (%)85.9

Interactive version: theaggregate.ai/model?slug=chocolatine-2-14b-instruct-v2-0-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.