Compare · ModelsLive · 2 picked · head to head
Mistral Small 3.1 24B 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·Mistral Small 3.1 24Bgeneral·Mistral Small 3.2 24Bmath·Mistral Small 3.2 24B
Hype vs Reality
Attention vs performance
Mistral Small 3.1 24B
#202 by perf·no signal
Mistral Small 3.2 24B
#292 by perf·no signal
Best value
Mistral Small 3.2 24B
1.4x better value than Mistral Small 3.1 24B
Mistral Small 3.1 24B
87.0 pts/$
$0.45/M
Mistral Small 3.2 24B
119.5 pts/$
$0.20/M
Vendor risk
Who is behind the model
Mistral AI
$24.0B·Tier 1
Mistral AI
$24.0B·Tier 1
Head to head
4 benchmarks · 2 models
Mistral Small 3.1 24BMistral 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.
Mistral Small 3.1 24B
0.0
Mistral Small 3.2 24B
0.0
Dtbench
Mistral Small 3.2 24B leads by +2.0
Mistral Small 3.1 24B
31.1
Mistral Small 3.2 24B
33.1
GPQA diamond
Mistral Small 3.2 24B leads by +0.9
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Mistral Small 3.1 24B
31.2
Mistral Small 3.2 24B
32.1
OTIS Mock AIME 2024-2025
Mistral Small 3.2 24B leads by +24.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Mistral Small 3.1 24B
5.7
Mistral Small 3.2 24B
30.2
Full benchmark table
| Benchmark | Mistral Small 3.1 24B | 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 | 31.1 | 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. | 31.2 | 32.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 5.7 | 30.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.35 | $0.56 | 128K tokens (~64 books) | $4.02 | |
| $0.10 | $0.30 | 256K tokens (~128 books) | $1.50 |