Compare · ModelsLive · 2 picked · head to head
gpt-oss-20b vs gpt-oss-20b (free)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
gpt-oss-20b wins on 6/7 benchmarks
gpt-oss-20b wins 6 of 7 shared benchmarks. Leads in math · knowledge · language.
Category leads
speed·gpt-oss-20b (free)math·gpt-oss-20bknowledge·gpt-oss-20blanguage·gpt-oss-20bcoding·gpt-oss-20b
Hype vs Reality
Attention vs performance
gpt-oss-20b
#97 by perf·no signal
gpt-oss-20b (free)
#31 by perf·no signal
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
7 benchmarks · 2 models
gpt-oss-20bgpt-oss-20b (free)
Artificial Analysis · Quality Index
gpt-oss-20b (free) leads by +5.9
gpt-oss-20b
9.0
gpt-oss-20b (free)
14.9
OpenCompass · AIME2025
gpt-oss-20b
87.9
gpt-oss-20b (free)
87.9
OpenCompass · GPQA-Diamond
gpt-oss-20b
68.9
gpt-oss-20b (free)
68.9
OpenCompass · HLE
gpt-oss-20b
11.6
gpt-oss-20b (free)
11.6
OpenCompass · IFEval
gpt-oss-20b
88.9
gpt-oss-20b (free)
88.9
OpenCompass · LiveCodeBenchV6
gpt-oss-20b
68.4
gpt-oss-20b (free)
68.4
OpenCompass · MMLU-Pro
gpt-oss-20b
72.8
gpt-oss-20b (free)
72.8
Full benchmark table
| Benchmark | gpt-oss-20b | gpt-oss-20b (free) |
|---|---|---|
Artificial Analysis · Quality Index | 9.0 | 14.9 |
OpenCompass · AIME2025 | 87.9 | 87.9 |
OpenCompass · GPQA-Diamond | 68.9 | 68.9 |
OpenCompass · HLE | 11.6 | 11.6 |
OpenCompass · IFEval | 88.9 | 88.9 |
OpenCompass · LiveCodeBenchV6 | 68.4 | 68.4 |
OpenCompass · MMLU-Pro | 72.8 | 72.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.02 | $0.09 | 131K tokens (~66 books) | $0.36 | |
| $0.00 | $0.00 | 131K tokens (~66 books) | — |