Devstral 2
MistralMistral
Release Date
2025-12-09
Parameters
—
Context Length
—
Modalities
—
Capability Radar
36
general
32
coding
40
reasoning
39
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 203 | 40.0 | AA |
| General Ranking | 244 | 42.0 | AA |
| Math Reasoning | 233 | 37.0 | AA |
| Science | 266 | 40.0 | AA |
Benchmark Scores (LLM Stats)
No benchmark data available
AA Evaluation Indices
Math Index36.7
Coding Index23.7
Intelligence Index22.0
Mmlu Pro0.8
Gpqa0.6
Livecodebench0.4
Ifbench0.4
Aime 250.4
Scicode0.3
Lcr0.3
Tau20.2
Terminalbench Hard0.2
Hle0.0
LLM Stats Category Scores
No category score data available
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec70.0 tokens/s
Time to First Token0.75s
Time to Answer0.75s
Available Providers
(LS internal units)No provider data available
External Sources
No external links available