Compare · ModelsLive · 2 picked · head to head
Gemma 2 27B vs Mistral 7B V0.1
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemma 2 27B wins on 8/9 benchmarks
Gemma 2 27B wins 8 of 9 shared benchmarks. Leads in math · general · knowledge.
Category leads
math·Gemma 2 27Bgeneral·Gemma 2 27Bknowledge·Gemma 2 27Blanguage·Gemma 2 27Breasoning·Mistral 7B V0.1
Hype vs Reality
Attention vs performance
Gemma 2 27B
#220 by perf·#7 by attention
Mistral 7B V0.1
#176 by perf·no signal
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
Mistral AI
$14.0B·Tier 1
Head to head
9 benchmarks · 2 models
Gemma 2 27BMistral 7B V0.1
GSM8K
Gemma 2 27B leads by +30.5
Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve.
Gemma 2 27B
84.9
Mistral 7B V0.1
54.4
BBH (HuggingFace)
Gemma 2 27B leads by +27.3
Gemma 2 27B
49.3
Mistral 7B V0.1
22.0
GPQA
Gemma 2 27B leads by +11.1
Gemma 2 27B
16.7
Mistral 7B V0.1
5.6
IFEval
Gemma 2 27B leads by +55.9
Gemma 2 27B
79.8
Mistral 7B V0.1
23.9
MATH Level 5
Gemma 2 27B leads by +20.9
Gemma 2 27B
23.9
Mistral 7B V0.1
3.0
MMLU-PRO
Gemma 2 27B leads by +16.0
Gemma 2 27B
38.4
Mistral 7B V0.1
22.4
MUSR
Mistral 7B V0.1 leads by +1.6
Gemma 2 27B
9.1
Mistral 7B V0.1
10.7
MMLU
Gemma 2 27B leads by +17.6
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Gemma 2 27B
67.6
Mistral 7B V0.1
50.0
PIQA
Gemma 2 27B leads by +1.4
PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks.
Gemma 2 27B
67.4
Mistral 7B V0.1
66.0
Full benchmark table
| Benchmark | Gemma 2 27B | Mistral 7B V0.1 |
|---|---|---|
GSM8K Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve. | 84.9 | 54.4 |
BBH (HuggingFace) | 49.3 | 22.0 |
GPQA | 16.7 | 5.6 |
IFEval | 79.8 | 23.9 |
MATH Level 5 | 23.9 | 3.0 |
MMLU-PRO | 38.4 | 22.4 |
MUSR | 9.1 | 10.7 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 67.6 | 50.0 |
PIQA PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks. | 67.4 | 66.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.65 | $0.65 | 8K tokens (~4 books) | $6.50 | |
| — | — | — | — |