Mistral Small 3
MistralMistral
Release Date
2025-01-30
Parameters
—
Context Length
33K
Modalities
text
Capability Radar
27
general
25
coding
19
reasoning
30
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 398 | 14.0 | AA |
| General Ranking | 380 | 28.0 | AA |
| Math Reasoning | 311 | 18.0 | AA |
| Science | 360 | 30.0 | AA |
Benchmark Scores (LLM Stats)
No benchmark data available
AA Evaluation Indices
Intelligence Index12.7
Math Index4.3
Math 5000.7
Mmlu Pro0.7
Gpqa0.5
Ifbench0.3
Livecodebench0.3
Scicode0.2
Tau20.2
Aime0.1
Aime 250.0
Hle0.0
Lcr0.0
LLM Stats Category Scores
No category score data available
Pricing
Input Price$0.075 / 1M tokens
Output Price$0.19 / 1M tokens
Blended Price (3:1)$0.104 / 1M tokens
Speed
Tokens/sec152.5 tokens/s
Time to First Token0.50s
Time to Answer0.50s
Available Providers
(LS internal units)No provider data available
External Sources
No external links available