Compare · ModelsLive · 2 picked · head to head
Claude 3.5 Haiku vs Mistral Medium 3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Mistral Medium 3 wins on 4/4 benchmarks
Mistral Medium 3 wins 4 of 4 shared benchmarks. Leads in math · knowledge.
Category leads
math·Mistral Medium 3knowledge·Mistral Medium 3
Hype vs Reality
Attention vs performance
Claude 3.5 Haiku
#157 by perf·no signal
Mistral Medium 3
#143 by perf·no signal
Best value
Mistral Medium 3
2.2x better value than Claude 3.5 Haiku
Claude 3.5 Haiku
15.5 pts/$
$2.40/M
Mistral Medium 3
33.3 pts/$
$1.20/M
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
Mistral AI
$14.0B·Tier 1
Head to head
4 benchmarks · 2 models
Claude 3.5 HaikuMistral Medium 3
FrontierMath-2025-02-28-Private
Mistral Medium 3 leads by +0.0
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude 3.5 Haiku
0.3
Mistral Medium 3
0.3
GPQA diamond
Mistral Medium 3 leads by +28.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude 3.5 Haiku
17.5
Mistral Medium 3
46.0
MATH level 5
Mistral Medium 3 leads by +35.3
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude 3.5 Haiku
46.4
Mistral Medium 3
81.6
OTIS Mock AIME 2024-2025
Mistral Medium 3 leads by +27.9
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude 3.5 Haiku
4.2
Mistral Medium 3
32.1
Full benchmark table
| Benchmark | Claude 3.5 Haiku | Mistral Medium 3 |
|---|---|---|
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. | 0.3 | 0.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 17.5 | 46.0 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 46.4 | 81.6 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 4.2 | 32.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Claude 3.5 Haiku | $0.80 | $4.00 | 200K tokens (~100 books) | $16.00 |
| Mistral Medium 3 | $0.40 | $2.00 | 131K tokens (~66 books) | $8.00 |