Compare · ModelsLive · 2 picked · head to head
Claude 3.5 Sonnet vs Mistral Large 4
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Mistral Large 4 wins on 3/3 benchmarks
Mistral Large 4 wins 3 of 3 shared benchmarks. Leads in general · knowledge · math.
Category leads
general·Mistral Large 4knowledge·Mistral Large 4math·Mistral Large 4
Hype vs Reality
Attention vs performance
Claude 3.5 Sonnet
#205 by perf·no signal
Mistral Large 4
#221 by perf·#19 by attention
Best value
Mistral Large 4
Claude 3.5 Sonnet
n/a
no price
Mistral Large 4
27.4 pts/$
$1.40/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Mistral AI
$24.0B·Tier 1
Head to head
3 benchmarks · 2 models
Claude 3.5 SonnetMistral Large 4
Dtbench
Mistral Large 4 leads by +34.1
Claude 3.5 Sonnet
46.3
Mistral Large 4
80.4
GPQA diamond
Mistral Large 4 leads by +51.8
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 Sonnet
38.7
Mistral Large 4
90.5
OTIS Mock AIME 2024-2025
Mistral Large 4 leads by +93.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude 3.5 Sonnet
6.4
Mistral Large 4
99.4
Full benchmark table
| Benchmark | Claude 3.5 Sonnet | Mistral Large 4 |
|---|---|---|
Dtbench | 46.3 | 80.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 38.7 | 90.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 6.4 | 99.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| n/a | n/a | n/a | n/a | |
| $0.70 | $2.10 | 1.0M tokens (~524 books) | $10.50 |