Mistral AI model product
Mistral Large 2
Mistral Large 2 is a 123B-parameter large language model from Mistral AI for code generation, mathematics, reasoning, multilingual use, and function calling.
Updated Sep 8, 2026. Default version: Mistral Large 2
LLMBoard Score9.0Mistral Large 2
Coverage0%4 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Mistral Large 2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Mistral Large 2 Benchmark Results
Benchmark scores for Mistral Large 2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMMLU French | Score82.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMT-Bench | Score86.30% | Rank06 | Participants12 | Percentile54.55% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score92.00% | Rank10 | Participants66 | Percentile86.15% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score93.00% | Rank18 | Participants48 | Percentile63.83% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score84.00% | Rank46 | Participants101 | Percentile55.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,314.03 rating | Rank175 | Participants210 | Percentile16.75% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,265.93 rating | Rank181 | Participants210 | Percentile13.88% | EvidenceA | Evaluated |
Mistral Large 2 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryfrench | Rank127 | Rating / score1,373.88 | Votes204 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank137 | Rating / score1,324.68 | Votes204 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank143 | Rating / score1,259.46 | Votes408 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank144 | Rating / score1,201.54 | Votes408 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank146 | Rating / score1,187.54 | Votes1,249 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank146 | Rating / score1,233.60 | Votes1,249 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank149 | Rating / score1,302.19 | Votes1,230 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank153 | Rating / score1,253.71 | Votes1,230 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank153 | Rating / score1,157.08 | Votes170 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank154 | Rating / score1,267.25 | Votes153 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank154 | Rating / score1,213.23 | Votes170 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank157 | Rating / score1,307.55 | Votes153 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank159 | Rating / score1,290.02 | Votes7,002 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank164 | Rating / score1,338.51 | Votes2,735 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank167 | Rating / score1,302.40 | Votes12,224 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank168 | Rating / score1,286.88 | Votes6,692 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank168 | Rating / score1,288.06 | Votes6,664 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank169 | Rating / score1,336.81 | Votes24,863 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank169 | Rating / score1,297.95 | Votes5,745 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank170 | Rating / score1,299.13 | Votes18,321 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank171 | Rating / score1,301.44 | Votes2,505 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank171 | Rating / score1,330.56 | Votes7,485 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank171 | Rating / score1,304.07 | Votes5,748 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank172 | Rating / score1,332.73 | Votes7,818 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank172 | Rating / score1,343.09 | Votes12,143 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank173 | Rating / score1,265.37 | Votes5,745 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank173 | Rating / score1,261.48 | Votes6,664 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank173 | Rating / score1,319.50 | Votes12,682 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank174 | Rating / score1,240.26 | Votes3,933 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank174 | Rating / score1,304.16 | Votes3,933 | ObservationsN/A | Result date |
Mistral Large 2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Mistral Large 2 Runtime Performance
Provider-specific output speed and catalog latency for Mistral Large 2. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed42.00 tok/s | Catalog Latency0.40 s | Max Input128K | Max Output128K | Updated |
| ProviderMistral AI | Output Speed0.10 tok/s | Catalog Latency0.50 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Mistral Large 2 Specifications
Technical details for the model's default version.
- Version
- Mistral Large 2
- Released
- Jul 24, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 123B
- Context window
- 128K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Mistral Research License
Mistral Large 2 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMistral Large 2 | Released | LLMBoard8.99 | Parameters123B | Context128K | Max output128K | Open weightsYes | LicenseMistral Research License |
Models similar to Mistral Large 2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Mistral Small 3.1 24B
Mistral AI
MA
Mistral Small 3 24B
Mistral AI
MA
Mistral Small 3.2 24B
Mistral AI
MA
Mistral Large 3
Mistral AI
MA
Devstral Small 1.1
Mistral AI
MA
Codestral 22B
Mistral AI
What is Mistral Large 2?
Key information about Mistral Large 2 and its available data.
Mistral Large 2 is a large language model from Mistral AI with a 128k context window and support for dozens of languages. It is designed for instruction-following, code generation, mathematics, reasoning, and advanced function calling.
Data as of 2026-09-08.
FAQ
Common questions about Mistral Large 2.
When was Mistral Large 2 released?
Mistral Large 2's default version was released on Jul 24, 2024.
How much does Mistral Large 2 cost?
No official standard PAYG price is currently available for Mistral Large 2.
Who created Mistral Large 2?
Mistral Large 2 was created by Mistral AI.
What is the context window for Mistral Large 2?
The default version has a 128K token context window.
Is Mistral Large 2 open weight?
Yes. The default version is marked as open weight under Mistral Research License.
How many API providers offer Mistral Large 2?
No provider offering is currently linked to the default version.