Compare · ModelsLive · 2 picked · head to head
Mistral Large vs o3 Mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
o3 Mini wins on 6/7 benchmarks
o3 Mini wins 6 of 7 shared benchmarks. Leads in general · math · knowledge.
Category leads
general·o3 Minimath·o3 Miniknowledge·o3 Minireasoning·o3 Mini
Hype vs Reality
Attention vs performance
Mistral Large
#185 by perf·#19 by attention
o3 Mini
#239 by perf·no signal
Best value
o3 Mini
1.2x better value than Mistral Large
Mistral Large
10.2 pts/$
$4.00/M
o3 Mini
11.8 pts/$
$2.75/M
Vendor risk
Who is behind the model
Mistral AI
$14.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
7 benchmarks · 2 models
Mistral Largeo3 Mini
Dtbench
o3 Mini leads by +21.5
Mistral Large
26.5
o3 Mini
48.0
FrontierMath-2025-02-28-Private
o3 Mini leads by +11.8
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Mistral Large
0.6
o3 Mini
12.4
GPQA diamond
o3 Mini leads by +51.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Mistral Large
18.4
o3 Mini
69.4
Lech Mazur Writing
Mistral Large leads by +7.3
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
Mistral Large
69.0
o3 Mini
61.7
MATH level 5
o3 Mini leads by +72.0
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Mistral Large
24.5
o3 Mini
96.5
OTIS Mock AIME 2024-2025
o3 Mini leads by +75.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Mistral Large
1.9
o3 Mini
76.9
SimpleBench
o3 Mini leads by +0.4
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Mistral Large
7.0
o3 Mini
7.4
Full benchmark table
| Benchmark | Mistral Large | o3 Mini |
|---|---|---|
Dtbench | 26.5 | 48.0 |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 0.6 | 12.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 18.4 | 69.4 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 69.0 | 61.7 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 24.5 | 96.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 1.9 | 76.9 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 7.0 | 7.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $6.00 | 128K tokens (~64 books) | $30.00 | |
| $1.10 | $4.40 | 200K tokens (~100 books) | $19.25 |