Compare · ModelsLive · 2 picked · head to head
GPT-4.5 vs Mistral Large 2407
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-4.5 wins on 5/5 benchmarks
GPT-4.5 wins 5 of 5 shared benchmarks. Leads in knowledge · math · reasoning.
Category leads
knowledge·GPT-4.5math·GPT-4.5reasoning·GPT-4.5
Hype vs Reality
Attention vs performance
GPT-4.5
#166 by perf·no signal
Mistral Large 2407
#147 by perf·no signal
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Mistral AI
$14.0B·Tier 1
Head to head
5 benchmarks · 2 models
GPT-4.5Mistral Large 2407
GPQA diamond
GPT-4.5 leads by +26.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4.5
58.3
Mistral Large 2407
32.0
Lech Mazur Writing
GPT-4.5 leads by +6.6
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
GPT-4.5
75.6
Mistral Large 2407
69.0
MATH level 5
GPT-4.5 leads by +33.8
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-4.5
78.6
Mistral Large 2407
44.8
OTIS Mock AIME 2024-2025
GPT-4.5 leads by +29.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4.5
37.7
Mistral Large 2407
8.4
SimpleBench
GPT-4.5 leads by +14.4
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-4.5
21.4
Mistral Large 2407
7.0
Full benchmark table
| Benchmark | GPT-4.5 | Mistral Large 2407 |
|---|---|---|
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 58.3 | 32.0 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 75.6 | 69.0 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 78.6 | 44.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 37.7 | 8.4 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 21.4 | 7.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| $2.00 | $6.00 | 131K tokens (~66 books) | $30.00 |