Compare · ModelsLive · 2 picked · head to head
Gemini 3 Pro vs gpt-oss-20b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3 Pro wins on 5/6 benchmarks
Gemini 3 Pro wins 5 of 6 shared benchmarks. Leads in arena · knowledge · language.
Category leads
arena·Gemini 3 Proknowledge·Gemini 3 Prolanguage·Gemini 3 Promath·gpt-oss-20breasoning·Gemini 3 Pro
Hype vs Reality
Attention vs performance
Gemini 3 Pro
#38 by perf·no signal
gpt-oss-20b
#22 by perf·no signal
Vendor risk
Who is behind the model
Google DeepMind
$4.00T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
6 benchmarks · 2 models
Gemini 3 Progpt-oss-20b
Chatbot Arena Elo · Overall
Gemini 3 Pro leads by +168.5
Gemini 3 Pro
1486.2
gpt-oss-20b
1317.7
HELM · GPQA
Gemini 3 Pro leads by +20.9
Gemini 3 Pro
80.3
gpt-oss-20b
59.4
HELM · IFEval
Gemini 3 Pro leads by +14.4
Gemini 3 Pro
87.6
gpt-oss-20b
73.2
HELM · MMLU-Pro
Gemini 3 Pro leads by +16.3
Gemini 3 Pro
90.3
gpt-oss-20b
74.0
HELM · Omni-MATH
gpt-oss-20b leads by +0.9
Gemini 3 Pro
55.6
gpt-oss-20b
56.5
HELM · WildBench
Gemini 3 Pro leads by +12.2
Gemini 3 Pro
85.9
gpt-oss-20b
73.7
Full benchmark table
| Benchmark | Gemini 3 Pro | gpt-oss-20b |
|---|---|---|
Chatbot Arena Elo · Overall | 1486.2 | 1317.7 |
HELM · GPQA | 80.3 | 59.4 |
HELM · IFEval | 87.6 | 73.2 |
HELM · MMLU-Pro | 90.3 | 74.0 |
HELM · Omni-MATH | 55.6 | 56.5 |
HELM · WildBench | 85.9 | 73.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Gemini 3 Pro | — | — | — | — |
| gpt-oss-20b | $0.03 | $0.14 | 131K tokens (~66 books) | $0.57 |