MMODELYST
Models/Mistral Small (Feb '24)
MDL

Mistral Small (Feb '24)

Mistral

Verified against Artificial Analysis · Jul 13, 2026
Capability
37
percentile index
Price /M
$1 / $3
in / out
Context
Avg score
26.2
6 benchmarks
AA Intelligence
3.6
index
Speed
160 tok/s
TTFT 0.5s
Released
Feb 26, 2024
About

Mistral Small (Feb '24) is a open-weights model in the Mistral family from Mistral. Benchmarked on 6 evals, averaging 26.2.

Benchmark scores · 6
avg 26.2 — higher is better
MATH
56.2
MMLU-Pro
41.9
GPQA Diamond
30.2
SciCode
13.4
LiveCodeBench
11.1
Humanity's Last Exam
4.4
Details
PublisherMistral
FamilyMistral
Parameters
License
WeightsOpen
ReleasedFeb 26, 2024
Performance & price
Output speed160 tok/s
Latency (TTFT)0.5s
Price in / out$1 / $3 per 1M
Blended price$1.5 / 1M

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$3/M