Compare · ModelsLive · 2 picked · head to head
Phi-1.5 vs Llama 3.2 3B Instruct (free)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Llama 3.2 3B Instruct (free) wins on 4/6 benchmarks
Llama 3.2 3B Instruct (free) wins 4 of 6 shared benchmarks. Leads in general · math · reasoning.
Category leads
general·Llama 3.2 3B Instruct (free)knowledge·Phi-1.5language·Phi-1.5math·Llama 3.2 3B Instruct (free)reasoning·Llama 3.2 3B Instruct (free)
Hype vs Reality
Attention vs performance
Phi-1.5
#221 by perf·no signal
Llama 3.2 3B Instruct (free)
#232 by perf·no signal
Vendor risk
Who is behind the model
Microsoft
$3.00T·Big Tech
Meta AI
$1.50T·Tier 1
Head to head
6 benchmarks · 2 models
Phi-1.5Llama 3.2 3B Instruct (free)
BBH (HuggingFace)
Llama 3.2 3B Instruct (free) leads by +6.8
Phi-1.5
7.5
Llama 3.2 3B Instruct (free)
14.2
GPQA
Phi-1.5
2.4
Llama 3.2 3B Instruct (free)
2.4
IFEval
Phi-1.5 leads by +7.0
Phi-1.5
20.3
Llama 3.2 3B Instruct (free)
13.4
MATH Level 5
Llama 3.2 3B Instruct (free) leads by +0.1
Phi-1.5
1.8
Llama 3.2 3B Instruct (free)
1.9
MMLU-PRO
Llama 3.2 3B Instruct (free) leads by +8.9
Phi-1.5
7.7
Llama 3.2 3B Instruct (free)
16.5
MUSR
Llama 3.2 3B Instruct (free) leads by +0.4
Phi-1.5
3.4
Llama 3.2 3B Instruct (free)
3.8
Full benchmark table
| Benchmark | Phi-1.5 | Llama 3.2 3B Instruct (free) |
|---|---|---|
BBH (HuggingFace) | 7.5 | 14.2 |
GPQA | 2.4 | 2.4 |
IFEval | 20.3 | 13.4 |
MATH Level 5 | 1.8 | 1.9 |
MMLU-PRO | 7.7 | 16.5 |
MUSR | 3.4 | 3.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| $0.00 | $0.00 | 131K tokens (~66 books) | — |