Compare · ModelsLive · 2 picked · head to head
SmolLM2 135M vs Gpt2 Medium
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gpt2 Medium wins on 3/6 benchmarks
Gpt2 Medium wins 3 of 6 shared benchmarks. Leads in knowledge · language.
Category leads
general·SmolLM2 135Mknowledge·Gpt2 Mediumlanguage·Gpt2 Mediummath·SmolLM2 135Mreasoning·SmolLM2 135M
Hype vs Reality
Attention vs performance
SmolLM2 135M
#236 by perf·no signal
Gpt2 Medium
#234 by perf·no signal
Vendor risk
Who is behind the model
HF
Hugging Face TB
private · undisclosed
OpenAI
$840.0B·Tier 1
Head to head
6 benchmarks · 2 models
SmolLM2 135MGpt2 Medium
BBH (HuggingFace)
SmolLM2 135M leads by +1.0
SmolLM2 135M
3.7
Gpt2 Medium
2.7
GPQA
Gpt2 Medium leads by +1.7
SmolLM2 135M
0.0
Gpt2 Medium
1.7
IFEval
Gpt2 Medium leads by +3.9
SmolLM2 135M
18.2
Gpt2 Medium
22.1
MATH Level 5
SmolLM2 135M leads by +0.4
SmolLM2 135M
1.2
Gpt2 Medium
0.8
MMLU-PRO
Gpt2 Medium leads by +1.0
SmolLM2 135M
1.1
Gpt2 Medium
2.0
MUSR
SmolLM2 135M leads by +3.9
SmolLM2 135M
10.0
Gpt2 Medium
6.2
Full benchmark table
| Benchmark | SmolLM2 135M | Gpt2 Medium |
|---|---|---|
BBH (HuggingFace) | 3.7 | 2.7 |
GPQA | 0.0 | 1.7 |
IFEval | 18.2 | 22.1 |
MATH Level 5 | 1.2 | 0.8 |
MMLU-PRO | 1.1 | 2.0 |
MUSR | 10.0 | 6.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
HF SmolLM2 135M | — | — | — | — |
| — | — | — | — |