Compare · ModelsLive · 2 picked · head to head
gpt-oss-20b vs Gemini 2.0 Flash (Dec 2024)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
gpt-oss-20b wins on 3/5 benchmarks
gpt-oss-20b wins 3 of 5 shared benchmarks. Leads in knowledge · math.
Category leads
knowledge·gpt-oss-20blanguage·Gemini 2.0 Flash (Dec 2024)math·gpt-oss-20breasoning·Gemini 2.0 Flash (Dec 2024)
Hype vs Reality
Attention vs performance
gpt-oss-20b
#29 by perf·no signal
Gemini 2.0 Flash (Dec 2024)
#130 by perf·no signal
Best value
gpt-oss-20b
gpt-oss-20b
797.6 pts/$
$0.08/M
Gemini 2.0 Flash (Dec 2024)
—
no price
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Google DeepMind
$4.00T·Tier 1
Head to head
5 benchmarks · 2 models
gpt-oss-20bGemini 2.0 Flash (Dec 2024)
HELM · GPQA
gpt-oss-20b leads by +3.8
gpt-oss-20b
59.4
Gemini 2.0 Flash (Dec 2024)
55.6
HELM · IFEval
Gemini 2.0 Flash (Dec 2024) leads by +10.9
gpt-oss-20b
73.2
Gemini 2.0 Flash (Dec 2024)
84.1
HELM · MMLU-Pro
gpt-oss-20b leads by +0.3
gpt-oss-20b
74.0
Gemini 2.0 Flash (Dec 2024)
73.7
HELM · Omni-MATH
gpt-oss-20b leads by +10.6
gpt-oss-20b
56.5
Gemini 2.0 Flash (Dec 2024)
45.9
HELM · WildBench
Gemini 2.0 Flash (Dec 2024) leads by +6.3
gpt-oss-20b
73.7
Gemini 2.0 Flash (Dec 2024)
80.0
Full benchmark table
| Benchmark | gpt-oss-20b | Gemini 2.0 Flash (Dec 2024) |
|---|---|---|
HELM · GPQA | 59.4 | 55.6 |
HELM · IFEval | 73.2 | 84.1 |
HELM · MMLU-Pro | 74.0 | 73.7 |
HELM · Omni-MATH | 56.5 | 45.9 |
HELM · WildBench | 73.7 | 80.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.03 | $0.14 | 131K tokens (~66 books) | $0.57 | |
| — | — | — | — |