Compare · ModelsLive · 2 picked · head to head
Distilgpt2 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 · math.
Category leads
general·Distilgpt2knowledge·Gpt2 Mediumlanguage·Gpt2 Mediummath·Gpt2 Mediumreasoning·Distilgpt2
Hype vs Reality
Attention vs performance
Distilgpt2
#280 by perf·no signal
Gpt2 Medium
#275 by perf·no signal
Vendor risk
Who is behind the model
D
DistilBERT
private · undisclosed
OpenAI
$840.0B·Tier 1
Head to head
6 benchmarks · 2 models
Distilgpt2Gpt2 Medium
BBH (HuggingFace)
Distilgpt2 leads by +0.1
Distilgpt2
2.8
Gpt2 Medium
2.7
GPQA
Gpt2 Medium leads by +0.4
Distilgpt2
1.2
Gpt2 Medium
1.7
IFEval
Gpt2 Medium leads by +16.0
Distilgpt2
6.1
Gpt2 Medium
22.1
MATH Level 5
Gpt2 Medium leads by +0.2
Distilgpt2
0.6
Gpt2 Medium
0.8
MMLU-PRO
Distilgpt2 leads by +0.1
Distilgpt2
2.1
Gpt2 Medium
2.0
MUSR
Distilgpt2 leads by +5.0
Distilgpt2
11.2
Gpt2 Medium
6.2
Full benchmark table
| Benchmark | Distilgpt2 | Gpt2 Medium |
|---|---|---|
BBH (HuggingFace) | 2.8 | 2.7 |
GPQA | 1.2 | 1.7 |
IFEval | 6.1 | 22.1 |
MATH Level 5 | 0.6 | 0.8 |
MMLU-PRO | 2.1 | 2.0 |
MUSR | 11.2 | 6.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
D Distilgpt2 | — | — | — | — |
| — | — | — | — |