All Comparisons
Mistral Large 3 vs o4-mini
Mistral Large 3
Mistral AI 🇫🇷
17.1
#324—
lowo4-mini
OpenAI 🇺🇸
56.7
#172—
highBest Benchmark Score
o4-mini
56.7/100
Model Specifications
| Spec | Mistral Large 3 | o4-mini |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Release Date | Sep 2025 | Apr 2025 |
| Knowledge Cutoff | — | 2024-05-31 |
| Parameters | 675000000000B | Undisclosed |
| Context Window | — | — |
| Max Output | — | — |
| Open Source | Yes | No |
| License | apache_2_0 | proprietary |
| Tokenizer | — | — |
| Modality | — | — |
| Reasoning Model | No | No |
| Moderated | No | No |
Pricing Comparison
| Price (per 1M tokens) | Mistral Large 3 | o4-mini |
|---|
API Provider Pricing
Capabilities
| Feature | Mistral Large 3 | o4-mini |
|---|---|---|
| Text Input | ||
| Image Input (Vision) | ||
| Audio Input | ||
| Video Input | ||
| File Input | ||
| Image Output | ||
| Audio Output | ||
| Tool Use | ||
| Structured Output (JSON) | ||
| Streaming | ||
| Reasoning Tokens | ||
| Web Search | ||
| Temperature Control | ||
| Top-P Sampling | ||
| Stop Sequences | ||
| Seed (Reproducibility) | ||
| Log Probabilities |
Category Comparison
Benchmark-by-Benchmark
general
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| MMMLU | 74.2 | — |
coding
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| SWE-bench Verified | — | 68.1 |
math
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| AIME 2025 | — | 92.7 |
reasoning
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| GPQA Diamond | — | 81.4 |
| Humanity's Last Exam | — | 14.7 |
multimodal
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| MMMU | — | 81.6 |
| CharXiv Reasoning | — | 72 |
agent
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| BrowseComp | — | 51.5 |
| TAU-Bench Retail | — | 71.8 |
Category Winners
coding
55.5
math
74.6
reasoning
45.6
general
17.1
multimodal
61.6
agent
42.1