Mistral apache_2_0 Released Dec 4, 2025 Updated
Mistral Large 3 (675B Instruct 2512)
ToolsGuide Scores, rankings, test results and price.
Model summary
Summary
Mistral Large 3 (675B Instruct 2512) is Mistral's model, released Dec 4, 2025. It's ranked in 3 categories and does best at text: #203 of 416, with a ToolsGuide Score of 235 against a median of 235.
It also ranks #90 of 167 for vision (324), #137 of 147 for coding (181).
Its vision and coding score uses votes only, because it has published fewer than two of the tests used for those categories.
It costs $0.50 per million input tokens and $1.50 per million output tokens, close to the median text model ($0.43).
It has published results on 5 tests and has the top score on 1 of them, including AMC_2022_23.
Specifications
- Creator
- Mistral
- Licence
- apache_2_0
- Released
- Dec 4, 2025
- Context window
- 262K tokens
- Input price
- $0.50 / 1M
- Output price
- $1.50 / 1M
- Tests reported
- 5
- Settings ranked
- mistral-large-3, Mistral Large 3
Model comparison
Against the ten best text models.
Text score
ToolsGuide Score out of 1,000 · Higher is better
Vision score
ToolsGuide Score out of 1,000 · Higher is better
Input price
USD per 1M input tokens · Lower is better
Leaderboards
Where Mistral Large 3 (675B Instruct 2512) sits among the top 20 in each category.
Text
#203 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
Vision
#90 of 167 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
Coding
#137 of 147 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
By task
Scored from votes on each kind of prompt alone, on the same 1,000-point scale.
Score against price
Text · the 10 priced models ranked closest · up and to the left is better value
Against its nearest rivals
Text prompts by kind · ToolsGuide Score from votes · hover for values
- Mistral Large 3 (675B Instruct 2512)
-
qwen3-next-80b-a3b-instruct -
claude-3-5-sonnet-20241022
Text
mistral-large-3 · hover a bar for its rank
Vision
Mistral Large 3 · hover a bar for its rank
Coding
Mistral Large 3 · hover a bar for its rank
Test results
Every test Mistral Large 3 (675B Instruct 2512) has a published result on, out of 100%, with its rank among the models that took it.
GPQA
#215 / 256Graduate-level science questions written to be hard to look up.
43.9%
Self-reported
LiveCodeBench
#57 / 76LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.
34.4%
Self-reported
MMMLU
#28 / 51Multilingual Massive Multitask Language Understanding dataset released by OpenAI, featuring professionally translated MMLU test questions across 14 languages including Arabic, Bengali, German, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Swahili, Yoruba, and Chinese. Contains approximately 15,908 multiple-choice questions per language covering 57 subjects.
85.5%
Self-reported
SimpleQA
#31 / 47SimpleQA is a factuality benchmark developed by OpenAI that measures the short-form factual accuracy of large language models. The benchmark contains 4,326 short, fact-seeking questions that are adversarially collected and designed to have single, indisputable answers. Questions cover diverse topics from science and technology to entertainment, and the benchmark also measures model calibration by evaluating whether models know what they know.
23.8%
Self-reported
AMC_2022_23
#1 / 6American Mathematics Competition problems from the 2022-23 academic year, consisting of multiple-choice mathematics competition problems designed for high school students. These problems require advanced mathematical reasoning, problem-solving strategies, and mathematical knowledge covering topics like algebra, geometry, number theory, and combinatorics. The benchmark is derived from the official AMC competitions sponsored by the Mathematical Association of America.
52.0%
Self-reported