mistral-tiny — benchmark results

Provider: Mistral. Released 2023-12-04. Access: Open.

Unified ELO 1246 ± 27, rank #1626 of 1776 rated models, from 11 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LogicKor - Math4.14Score (0-10)48.7
LogicKor - Reasoning5.28Score (0-10)42.7
LogicKor - Coding6.5Score (0-10)37.4
InfiBench29.41Score (%)30
LogicKor - Writing5.71Score (0-10)29.9
LogicKor - Multi-Turn4.45Score (0-10)28.1
LogicKor4.76Score (0-10)25.7
LogicKor - Single-Turn5.07Score (0-10)23.5
LogicKor - Understanding5Score (0-10)17
LogicKor - Grammar1.92Score (0-10)5.8
Wolfram LLM Benchmarking Project8.2Correct Functionality (%)4.3

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