Intelligence
16 scoreMistral · Flagships Analysis
Mistral Large 3
Intelligence, Performance & Price Analysis
Canonical slug: mistral-large-3 · Canonical model registry at build time
Speed
53.0 output tokens/secLatency
1.19s TTFTInput Price
$0.50 / 1M tokensOutput Price
$1.50 / 1M tokensVerbosity
5.6M Output tokens from Intelligence Index 3 out of 4 units for Verbosity . CompExecutive Assessment
Routing Verdict & Tradeoffs
Ethen Routing Verdict
Capable everyday model
Mistral Large 3 scores 16 on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 17). Mistral Large 3 generates output at 53.0 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s). Mistral Large 3 costs $0.50 per 1M input tokens (better than average, median: $0.60) and $1.50 per 1M output tokens (better than average, median: $2.40), based on Mistral's API.
Good for routine tasks; route complex reasoning and premium workloads to stronger models.
Task Fit Assessment
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | viable | Intelligence score 16 handles routine reasoning but may struggle with open-ended agentic tasks. |
| High-volume chat & customer-facing | optimal | Output speed 53.0 tokens/sec is adequate for chat. |
| Latency-sensitive applications | optimal | TTFT 1.19s — adequate latency for most interactive use cases. |
| Cost-sensitive pipelines | optimal | Output pricing at $1.50 is reasonable for moderate volume. |
Cost Pressure Analysis
Medium
Pricing is moderate — input $0.50, output $1.50. Costs accumulate at volume but are manageable for valuable tasks.
Technical Specifications
Architecture and Limits
| Specification | Value | Validation Authority |
|---|---|---|
| Model type | Open weights | inferred |
| Reasoning | No | faq |
| Input modalities | Mistral Large 3 supports text and image input. | faq |
| Output modalities | Mistral Large 3 supports text output. | faq |
| Context window | 260k tokens | faq |
| Open weights / source | Yes, Mistral Large 3 is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | Mistral Large 3 has 675 billion parameters (41 billion active). | faq |
| Active parameters | 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. | faq |
| License | Mistral Large 3 is released under the Apache 2.0 license. This license allows commercial use. | faq |
| API availability | Yes, Mistral Large 3 is available via API through 3 providers. | faq |
Evidence charts
Profile visualizations
Charts are the same canonical evidence cards previously published for this slug, contained inside the D18D page grammar.
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.
Output Tokens per Intelligence Index Task
Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Methodology
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Mistral Large 3.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Frequently Asked Questions
Model FAQs & Technical Disclosures
Mistral Large 3 was released on December 2, 2025.
Mistral Large 3 was created by Mistral.
Mistral Large 3 scores 16 on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 17).
Mistral Large 3 generates output at 53.0 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s).
Mistral Large 3 has a time to first token (TTFT) of 1.19s (based on Mistral's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 2.33s).
Mistral Large 3 costs $0.50 per 1M input tokens (better than average, median: $0.60) and $1.50 per 1M output tokens (better than average, median: $2.40), 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 $0.60 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Mistral Large 3 generated 5.6M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 4.8M).
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.
Mistral Large 3 achieves a score of 16 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.
Mistral Large 3 is available through 3 API providers.