Compare · ModelsLive · 2 picked · head to head
Gemini 2.5 Flash vs Mistral Medium 3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 2.5 Flash wins on 4/5 benchmarks
Gemini 2.5 Flash wins 4 of 5 shared benchmarks. Leads in general · math · knowledge.
Category leads
general·Gemini 2.5 Flashmath·Gemini 2.5 Flashknowledge·Gemini 2.5 Flash
Hype vs Reality
Attention vs performance
Gemini 2.5 Flash
#191 by perf·no signal
Mistral Medium 3
#192 by perf·no signal
Best value
Mistral Medium 3
1.2x better value than Gemini 2.5 Flash
Gemini 2.5 Flash
28.1 pts/$
$1.40/M
Mistral Medium 3
32.8 pts/$
$1.20/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
Mistral AI
$14.0B·Tier 1
Head to head
5 benchmarks · 2 models
Gemini 2.5 FlashMistral Medium 3
Dtbench
Gemini 2.5 Flash leads by +23.8
Gemini 2.5 Flash
60.9
Mistral Medium 3
37.1
FrontierMath-2025-02-28-Private
Gemini 2.5 Flash leads by +7.9
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Gemini 2.5 Flash
8.5
Mistral Medium 3
0.6
HLE
Gemini 2.5 Flash leads by +7.7
HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. Claude Opus 4.7 scores 46.9% without tools and 54.7% with tools · making it one of the few benchmarks where the top score is below 60%.
Gemini 2.5 Flash
7.7
Mistral Medium 3
0.0
Lech Mazur Writing
Mistral Medium 3 leads by +0.8
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
Gemini 2.5 Flash
76.5
Mistral Medium 3
77.3
OTIS Mock AIME 2024-2025
Gemini 2.5 Flash leads by +40.9
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 2.5 Flash
73.0
Mistral Medium 3
32.1
Full benchmark table
| Benchmark | Gemini 2.5 Flash | Mistral Medium 3 |
|---|---|---|
Dtbench | 60.9 | 37.1 |
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. | 8.5 | 0.6 |
HLE HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. Claude Opus 4.7 scores 46.9% without tools and 54.7% with tools · making it one of the few benchmarks where the top score is below 60%. | 7.7 | 0.0 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 76.5 | 77.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 73.0 | 32.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.30 | $2.50 | 1.0M tokens (~524 books) | $8.50 | |
| $0.40 | $2.00 | 131K tokens (~66 books) | $8.00 |