Mistral
Pixtral Large 2411
Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is available under the Mistral Research License (MRL) for research and educational use, and the Mistral Commercial License for experimentation, testing, and production for commercial purposes.
- Input / 1M tokens
- $2.00
- Output / 1M tokens
- $6.00
- Context window
- 131K tokens
- Provider
- Mistral
- Cached input / 1M
- $0.200
- Knowledge cutoff
- 2024-07-31
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- 52 t/s
- Time to first token
- 0.47s
Benchmarks
Intelligence, coding, and math indexes plus the underlying evaluation scores.
- Intelligence Index
- 14
- Coding Index
- —
- Math Index
- 2
- MMLU-Pro
- 70.1%
- GPQA
- 50.5%
- HLE
- 3.6%
- LiveCodeBench
- 26.1%
- SciCode
- 29.2%
- MATH-500
- 71.4%
- AIME
- 7.0%
Benchmarks via Artificial Analysis