Mistral AI model product
A 123B parameter model with strong capabilities in code generation, mathematics, and reasoning.
Updated Aug 12, 2026. Default version: Mistral Large 2
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Mistral Large 2.
| MMLU French | 82.8% | 01 | 1 | 100.0% | C | |
| MT-Bench | 86.3% | 06 | 12 | 54.5% | C | |
| HumanEval | 92.0% | 10 | 66 | 86.2% | C | |
| GSM8k | 93.0% | 18 | 48 | 63.8% | C | |
| MMLU | 84.0% | 46 | 100 | 54.5% | C |
Preference and agent-evaluation results for the default version.
| text style control | overall | 243 | 1314.2 | 45,459 | N/A | |
| text | overall | 253 | 1266.3 | 45,459 | N/A | |
| text style control | overall | 253 | 1305.4 | 28,073 | N/A | |
| text | overall | 254 | 1265.4 | 28,073 | N/A | |
| text style control | overall | 293 | 1242.0 | 62,436 | N/A | |
| text | overall | 300 | 1176.6 | 62,436 | N/A |
Provider-specific output speed and catalog latency for Mistral Large 2. Runtime does not affect the capability score.
| 42 tok/s | 0.4 s | 128K | 128K | ||
| Mistral AI | 0.1 tok/s | 0.5 s | 128K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
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.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Mistral Large 2 | 7.0 | 123B | 128K | 128K | No | Mistral Research License |
Key information about Mistral Large 2 and its available data.
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.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Mistral Large 2.
Mistral Large 2's default version was released on Jul 24, 2024.
No official standard PAYG price is currently available for Mistral Large 2.
Mistral Large 2 was created by Mistral AI.
The default version has a 128K token context window.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.
Nearby ranked alternatives include Mistral Small 3 24B, Phi 4 multimodal, Hermes 3 70B.