L-MChat-Small Benchmark Results

L-MChat-Small — benchmark results

Provider: Other. Released 2024-04-11. Access: Open.

Unified ELO 1257 ± 28, rank #1605 of 1776 rated models, from 14 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MuSR	9.27	Score	44.8
Open LLM Leaderboard - BBH	26.86	Score	42.2
Open LLM Leaderboard - IFEval	32.87	Score	30.8
Open LLM Leaderboard - MMLU-Pro	16.27	Score	25.2
Open LLM Leaderboard - GPQA	2.35	Score	22.1
Open LLM Leaderboard - MATH Level 5	3.78	Score	21.8
Open Chinese LLM - TruthfulQA MC	49.57	Accuracy (%)	16.5
Open Chinese LLM - GSM8K	7.66	Accuracy (%)	7.4
Open Chinese LLM - C-Eval Semantic	33.88	Accuracy (%)	3.9
Open Chinese LLM - CMMLU	33.06	Accuracy (%)	3.3
Open Chinese LLM - WinoGrande	51.7	Accuracy (%)	2.7
Open Chinese LLM Leaderboard	33.68	Average Score (%)	2.4

Interactive version: theaggregate.ai/model?slug=l-mchat-small · How the rankings work · Data refreshed daily, snapshot 2026-07-22.