Mistral Large 2 (Nov '24)
MistralMistralOpen WeightMistral Research License
Description
A 123B parameter model with strong capabilities in code generation, mathematics, and reasoning. Features enhanced multilingual support across dozens of languages, 128k context window, and advanced function calling capabilities. Excels in instruction-following and maintains concise outputs.
Release Date
2024-11-18
Parameters
123.0B
Context Length
—
Modalities
text
Capability Radar
30
general
21
coding
26
reasoning
33
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 350 | 19.0 | AA |
| General Ranking | 326 | 34.0 | AA |
| Math Reasoning | 287 | 25.0 | AA |
| Science | 319 | 34.0 | AA |
Benchmark Scores (LLM Stats)
Code
HumanEval
92.0%SR
Communication
MT-Bench
0.86 / 100SR
Finance
MMLU
84.0%SR
MMLU French
82.8%SR
Math
GSM8k
93.0%SR
AA Evaluation Indices
Intelligence Index15.1
Math Index14.0
Coding Index13.8
Math 5000.7
Mmlu Pro0.7
Gpqa0.5
Ifbench0.3
Tau20.3
Livecodebench0.3
Scicode0.3
Aime 250.1
Aime0.1
Terminalbench Hard0.1
Lcr0.1
Hle0.0
LLM Stats Category Scores
Code90
Communication90
Creativity90
General90
Math90
Reasoning90
Roleplay90
Finance80
Healthcare80
Language80
Legal80
Pricing
Input Price$2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$3 / 1M tokens
Speed
Tokens/sec32.1 tokens/s
Time to First Token0.57s
Time to Answer0.57s
Available Providers
(LS internal units)No provider data available