Compare · ModelsLive · 2 picked · head to head
Gemma 3 27B vs Mistral Small 3.1 24B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemma 3 27B wins on 4/5 benchmarks
Gemma 3 27B wins 4 of 5 shared benchmarks. Leads in knowledge · math.
Category leads
knowledge·Gemma 3 27Bgeneral·Mistral Small 3.1 24Bmath·Gemma 3 27B
Hype vs Reality
Attention vs performance
Gemma 3 27B
#212 by perf·#7 by attention
Mistral Small 3.1 24B
#194 by perf·no signal
Best value
Gemma 3 27B
1.6x better value than Mistral Small 3.1 24B
Gemma 3 27B
137.7 pts/$
$0.27/M
Mistral Small 3.1 24B
86.5 pts/$
$0.45/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
Gemma 3 27BMistral Small 3.1 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 3.1 24B
0.0
Dtbench
Mistral Small 3.1 24B leads by +10.2
Gemma 3 27B
20.9
Mistral Small 3.1 24B
31.1
GPQA diamond
Gemma 3 27B 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
30.3
Mistral Small 3.1 24B
30.0
MATH level 5
Gemma 3 27B leads by +27.3
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Gemma 3 27B
74.0
Mistral Small 3.1 24B
46.8
OTIS Mock AIME 2024-2025
Gemma 3 27B leads by +16.7
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemma 3 27B
22.4
Mistral Small 3.1 24B
5.7
Full benchmark table
| Benchmark | Gemma 3 27B | Mistral Small 3.1 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 | 31.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 30.3 | 30.0 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 74.0 | 46.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 22.4 | 5.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.08 | $0.45 | 131K tokens (~66 books) | $1.72 | |
| $0.35 | $0.56 | 128K tokens (~64 books) | $4.02 |