Compare · ModelsLive · 2 picked · head to head
o3 vs gpt-oss-20b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
o3 wins on 5/5 benchmarks
o3 wins 5 of 5 shared benchmarks. Leads in knowledge · language · math.
Category leads
knowledge·o3language·o3math·o3reasoning·o3
Hype vs Reality
Attention vs performance
o3
#67 by perf·no signal
gpt-oss-20b
#22 by perf·no signal
Best value
gpt-oss-20b
71.8x better value than o3
o3
11.0 pts/$
$5.00/M
gpt-oss-20b
792.9 pts/$
$0.09/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
5 benchmarks · 2 models
o3gpt-oss-20b
HELM · GPQA
o3 leads by +15.9
o3
75.3
gpt-oss-20b
59.4
HELM · IFEval
o3 leads by +13.7
o3
86.9
gpt-oss-20b
73.2
HELM · MMLU-Pro
o3 leads by +11.9
o3
85.9
gpt-oss-20b
74.0
HELM · Omni-MATH
o3 leads by +14.9
o3
71.4
gpt-oss-20b
56.5
HELM · WildBench
o3 leads by +12.4
o3
86.1
gpt-oss-20b
73.7
Full benchmark table
| Benchmark | o3 | gpt-oss-20b |
|---|---|---|
HELM · GPQA | 75.3 | 59.4 |
HELM · IFEval | 86.9 | 73.2 |
HELM · MMLU-Pro | 85.9 | 74.0 |
HELM · Omni-MATH | 71.4 | 56.5 |
HELM · WildBench | 86.1 | 73.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| o3 | $2.00 | $8.00 | 200K tokens (~100 books) | $35.00 |
| gpt-oss-20b | $0.03 | $0.14 | 131K tokens (~66 books) | $0.57 |