Skip to main content

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#RankScoreSource
Code Ranking350
19.0
AA
General Ranking326
34.0
AA
Math Reasoning287
25.0
AA
Science319
34.0
AA

Benchmark Scores (LLM Stats)

Code

HumanEval92.0%SR

Communication

MT-Bench0.86 / 100SR

Finance

MMLU84.0%SR
MMLU French82.8%SR

Math

GSM8k93.0%SR

AA Evaluation Indices

Intelligence Index
15.1
Math Index
14.0
Coding Index
13.8
Math 500
0.7
Mmlu Pro
0.7
Gpqa
0.5
Ifbench
0.3
Tau2
0.3
Livecodebench
0.3
Scicode
0.3
Aime 25
0.1
Aime
0.1
Terminalbench Hard
0.1
Lcr
0.1
Hle
0.0

LLM Stats Category Scores

Code
90
Communication
90
Creativity
90
General
90
Math
90
Reasoning
90
Roleplay
90
Finance
80
Healthcare
80
Language
80
Legal
80

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

External Sources