Compare · ModelsLive · 2 picked · head to head
Phi 3.5 Mini Instruct vs Gemma 2 27B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemma 2 27B wins on 5/6 benchmarks
Gemma 2 27B wins 5 of 6 shared benchmarks. Leads in general · knowledge · language.
Category leads
general·Gemma 2 27Bknowledge·Gemma 2 27Blanguage·Gemma 2 27Bmath·Gemma 2 27Breasoning·Phi 3.5 Mini Instruct
Hype vs Reality
Attention vs performance
Phi 3.5 Mini Instruct
#192 by perf·no signal
Gemma 2 27B
#175 by perf·no signal
Vendor risk
Who is behind the model
Microsoft
$3.00T·Big Tech
Google DeepMind
$4.00T·Tier 1
Head to head
6 benchmarks · 2 models
Phi 3.5 Mini InstructGemma 2 27B
BBH (HuggingFace)
Gemma 2 27B leads by +12.5
Phi 3.5 Mini Instruct
36.8
Gemma 2 27B
49.3
GPQA
Gemma 2 27B leads by +4.7
Phi 3.5 Mini Instruct
12.0
Gemma 2 27B
16.7
IFEval
Gemma 2 27B leads by +22.0
Phi 3.5 Mini Instruct
57.8
Gemma 2 27B
79.8
MATH Level 5
Gemma 2 27B leads by +4.2
Phi 3.5 Mini Instruct
19.6
Gemma 2 27B
23.9
MMLU-PRO
Gemma 2 27B leads by +5.4
Phi 3.5 Mini Instruct
32.9
Gemma 2 27B
38.4
MUSR
Phi 3.5 Mini Instruct leads by +1.0
Phi 3.5 Mini Instruct
10.1
Gemma 2 27B
9.1
Full benchmark table
| Benchmark | Phi 3.5 Mini Instruct | Gemma 2 27B |
|---|---|---|
BBH (HuggingFace) | 36.8 | 49.3 |
GPQA | 12.0 | 16.7 |
IFEval | 57.8 | 79.8 |
MATH Level 5 | 19.6 | 23.9 |
MMLU-PRO | 32.9 | 38.4 |
MUSR | 10.1 | 9.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Phi 3.5 Mini Instruct | — | — | — | — |
| Gemma 2 27B | $0.65 | $0.65 | 8K tokens (~4 books) | $6.50 |