RankingIA v0.6.1
EN

Mistral Large 4

Mistral

42.7#227 of 427 overall
Input / output
US$ 0,70 / US$ 2,10
US$ per 1M tokens
Context
—
tokens
Release
10/29/2026
release date
Weights
Closed
 
Speed
169 tok/s
first token in 2.88 s

Family history

The 5 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table
ModelReleasedScoreRankAA Intel.Elo Arena
Mistral Large 211/18/202417.4#416—1266
Mistral Large 3 251212/01/202517.5#414—1265
Mistral Large 312/02/202535.9#297—1428
Mistral Large 410/06/202643.9#209——
Mistral Large 410/29/202642.7#22726.01430

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
LiveBench weight 3 43.9 3% LiveBench
AA Intelligence Index weight 3 26.0 42% Artificial Analysis
Arena text (Elo) weight 2 1430 63% LMArena
Arena WebDev (Elo) weight 1 1544 66% LMArena
Arena vision (Elo) weight 0.5 1272 69% LMArena
Terminal-Bench weight 1 24.7 81% Artificial Analysis
LiveBench long agentic 8.8 10% LiveBench
LiveBench reasoning 83.9 45% LiveBench
LiveBench coding 60.0 7% LiveBench
LiveBench browser 0.6 3% LiveBench
LiveBench data analysis 76.5 48% LiveBench
LiveBench research 28.1 0% LiveBench
LiveBench design 65.6 19% LiveBench

By category

CategoryScoreRankMetrics
Agentic46.8#78LiveBench long agentic, Terminal-Bench
Coding40.7#79LiveBench coding, Arena WebDev (Elo)
Reasoning47.6#238LiveBench reasoning
Data analysis49.2#17LiveBench data analysis
Research25.0#358LiveBench research
Design45.0#71LiveBench design, Arena WebDev (Elo)
Browser use26.6#31LiveBench browser
Chat56.4#74Arena text (Elo)
Vision59.3#34Arena vision (Elo)

History

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.

Compare with other models

At the sources