EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

Mistral

Devstral Medium

Devstral Medium is a Mistral AI model profile from a lineup that spans compact Ministral models, specialist coding models, reasoning-oriented Magistral releases, and larger frontier open models. The local data makes its multilingual, coding, cost, and latency tradeoffs easier to compare against other providers.

Introducing Mistral 3

Operational Metrics

Output Speed71.4 tok/s
First Token0.50s
Blended Price$0.800/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseJul 10, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: TTFT

Rank #44 across 293 models.

0.50s

Watch Area: Math

Rank #248 across 269 models.

4.7

Watch Area: HLE

Rank #424 across 474 models.

3.8%

Watch Area: AIME

Rank #147 across 194 models.

6.7%

Strength Profile

Percentile score by analysis domain.

* Cost is inverted: lower input, output, and blended prices rank higher.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall18.7#254
Artificial Analysis Coding Indexcoding15.9#233
Artificial Analysis Math Indexmath4.7#248
MMLU-Proreasoning70.8%#216
GPQA
reasoning
49.2%
#343
Humanity's Last Examreasoning3.8%#424
LiveCodeBenchcoding33.7%#204
SciCodecoding, reasoning29.4%#253
MATH-500math70.7%#139
AIMEmath6.7%#147
Output Speedspeed71.4 tok/s#177
Time to First Tokenspeed0.50s#44
Blended Pricecost$0.800/M#148
Input Pricecost$0.400/M#153
Output Pricecost$2.00/M#147
Value Indexcost, overall23.4#181