This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
Mistral has launched a newer release, Mistral Large 4 Preview. We suggest considering it instead.
Mistral Large 3 Intelligence, Performance & Price Analysis
Model summary
Mistral Large 3 is below average in intelligence, but reasonably priced when comparing to other open weight non-reasoning models of similar size. It's also faster than average, however somewhat verbose. The model supports text and image input, outputs text, and has a 256k tokens context window.
Mistral Large 3 scores 9 on the Artificial Analysis Intelligence Index, placing it below average among comparable models (median: 12). When evaluating the Intelligence Index, it generated 9.8M tokens, which is somewhat verbose in comparison to the median of 7.5M.
Pricing for Mistral Large 3 is $0.50 per 1M input tokens (somewhat expensive, median: $0.47) and $1.50 per 1M output tokens (moderately priced, median: $1.59). On average, it costs $0.03 per task to evaluate Mistral Large 3 on the Intelligence Index.
At 79 tokens per second, Mistral Large 3 is faster than average (60).
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: text and image |
| Output modality | Supports: text |
| Context window | 256k ~384 A4 pages of size 12 Arial font |
| Total parameters | 675B |
| Active parameters | 41B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Measures the performance of models on specific capabilities and industries
Artificial Analysis Finance & Accounting Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, Elo
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Long context reasoning
Coding
Physics reasoning
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic interactive 3D experiences, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
AA-Briefcase v1.1
AA-Briefcase Elo
AA-Omniscience
AA-Omniscience Index
Openness Index
Artificial Analysis Openness Index: Score
Intelligence Index Comparisons
Intelligence Index vs. Cost per Task
Token Use
Output Tokens per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Speed
Measured by Output Speed (tokens per second)
Output Speed
Time per Intelligence Index Task
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Frequently Asked Questions
Common questions about Mistral Large 3
Mistral Large 3 was released on December 2, 2025.
Mistral Large 3 was created by Mistral.
Mistral Large 3 scores 9 on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 12).
Mistral Large 3 generates output at 79.5 tokens per second (based on Mistral's API), which is above average compared to other open weight non-reasoning models of similar size (median: 60.0 t/s).
Mistral Large 3 has a time to first token (TTFT) of 1.06s (based on Mistral's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.46s).
Mistral Large 3 costs $0.50 per 1M input tokens (better than average, median: $0.47) and $1.50 per 1M output tokens (better than average, median: $1.59), based on Mistral's API.
Mistral Large 3 costs $0.50 per 1M input tokens and $1.50 per 1M output tokens (based on Mistral's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.29 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, Mistral Large 3 generated 9.8M output tokens, which is better than average compared to other open weight non-reasoning models of similar size (median: 7.5M).
No, Mistral Large 3 is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Mistral Large 3 supports text and image input.
Mistral Large 3 supports text output.
Yes, Mistral Large 3 supports image input and can analyze, describe, and answer questions about images.
Yes, Mistral Large 3 is multimodal. It can process text and image input and generate text output.
Mistral Large 3 has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Mistral Large 3 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Mistral Large 3 has 675 billion parameters (41 billion active).
Mistral Large 3 is a Mixture of Experts (MoE) model with 675 billion total parameters, but only 41 billion active parameters are used during inference.
Mistral Large 3 is released under the Apache 2.0 license. This license allows commercial use. View license
Mistral Large 3 achieves a score of 9 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Mistral Large 3 is available via API through 3 providers. Compare API providers
Mistral Large 3 is available through 3 API providers. Compare providers