Chocolatine-2-14B-Instruct-v2.0b3: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1565 ± 34, rank #1471 of 10916 rated models, from 56 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - GPQA37.92Score94.6
Open LLM Leaderboard - MuSR47.81Score94.1
Open LLM Leaderboard - MMLU-Pro53.37Score93.6
Open Japanese LLM - Mbpp Pylint Check97.99Score (%)93.4
Open Japanese LLM - CG62.45Score (%)92.1
Open LLM Leaderboard - MATH Level 541.09Score91
Open Japanese LLM - Xlsum JA Bert Score JA F170.73Score (%)90.4
Open LLM Leaderboard - BBH64.69Score90.3
Open LLM Leaderboard - IFEval73.23Score87.5
Open Japanese LLM - Xlsum JA Rouge211.15Score (%)84.6
Open Japanese LLM - Xlsum JA RougeLsum25.75Score (%)84.4
Open Japanese LLM - SUM11.13Score (%)84.3

Interactive version: theaggregate.ai/model?slug=chocolatine-2-14b-instruct-v2-0b3 · How It Works · Data refreshed daily, snapshot 2026-11-08.