MMODELYST
Models/Mistral Medium 3.1
MDL

Mistral Medium 3.1

Mistral

Verified against Artificial Analysis · Jul 13, 2026
Capability
54
percentile index
Price /M
$0.4 / $2
in / out
Context
131.1K
tokens
Avg score
35.5
10 benchmarks
AA Intelligence
14.7
index
Speed
84 tok/s
TTFT 0.5s
Released
Aug 12, 2025
About

Mistral Medium 3.1 is a open-weights model in the Mistral family from Mistral. Benchmarked on 10 evals, averaging 35.5.

Benchmark scores · 10
avg 35.5 — higher is better
MMLU-Pro
68.3
GPQA Diamond
58.8
τ²-bench
40.6
LiveCodeBench
40.6
IFBench
39.8
AIME
38.3
SciCode
33.8
AA Long-Context Reasoning
19.7
Terminal-Bench Hard
10.6
Humanity's Last Exam
4.4
The research behind this model
all papers mentioning it →

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details
PublisherMistral
FamilyMistral
Parameters
License
WeightsOpen
ReleasedAug 12, 2025
Performance & price
Output speed84 tok/s
Latency (TTFT)0.5s
Price in / out$0.4 / $2 per 1M
Blended price$0.8 / 1M
Coding index20.5
Math index38.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$2/M