Compare · ModelsLive · 2 picked · head to head
Gemma 3 27B vs Mistral Small 3.2 24B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Mistral Small 3.2 24B wins on 3/4 benchmarks
Mistral Small 3.2 24B wins 3 of 4 shared benchmarks. Leads in general · math.
Category leads
knowledge·Gemma 3 27Bgeneral·Mistral Small 3.2 24Bmath·Mistral Small 3.2 24B
Hype vs Reality
Attention vs performance
Gemma 3 27B
#225 by perf·#7 by attention
Mistral Small 3.2 24B
#292 by perf·no signal
Best value
Gemma 3 27B
1.4x better value than Mistral Small 3.2 24B
Gemma 3 27B
170.2 pts/$
$0.21/M
Mistral Small 3.2 24B
119.5 pts/$
$0.20/M
Vendor risk
Who is behind the model
Google DeepMind
$3.53T·Tier 1
Mistral AI
$24.0B·Tier 1
Head to head
4 benchmarks · 2 models
Gemma 3 27BMistral Small 3.2 24B
Chess Puzzles
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemma 3 27B
0.0
Mistral Small 3.2 24B
0.0
Dtbench
Mistral Small 3.2 24B leads by +12.2
Gemma 3 27B
20.9
Mistral Small 3.2 24B
33.1
GPQA diamond
Mistral Small 3.2 24B leads by +0.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemma 3 27B
31.8
Mistral Small 3.2 24B
32.1
OTIS Mock AIME 2024-2025
Mistral Small 3.2 24B leads by +7.8
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemma 3 27B
22.4
Mistral Small 3.2 24B
30.2
Full benchmark table
| Benchmark | Gemma 3 27B | Mistral Small 3.2 24B |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 0.0 | 0.0 |
Dtbench | 20.9 | 33.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 31.8 | 32.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 22.4 | 30.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.08 | $0.35 | 131K tokens (~66 books) | $1.48 | |
| $0.10 | $0.30 | 256K tokens (~128 books) | $1.50 |