Compare · ModelsLive · 2 picked · head to head
Gemini 3.5 Flash vs gpt-oss-20b (free)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.5 Flash wins on 3/3 benchmarks
Gemini 3.5 Flash wins 3 of 3 shared benchmarks. Leads in speed.
Category leads
speed·Gemini 3.5 Flash
Hype vs Reality
Attention vs performance
Gemini 3.5 Flash
#82 by perf·#5 by attention
gpt-oss-20b (free)
#31 by perf·no signal
Best value
Gemini 3.5 Flash
Gemini 3.5 Flash
10.4 pts/$
$5.25/M
gpt-oss-20b (free)
n/a
$0.00/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
3 benchmarks · 2 models
Gemini 3.5 Flashgpt-oss-20b (free)
Artificial Analysis · Agentic Index
Gemini 3.5 Flash leads by +34.4
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
Gemini 3.5 Flash
37.5
gpt-oss-20b (free)
3.1
Artificial Analysis · Coding Index
Gemini 3.5 Flash leads by +49.4
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
Gemini 3.5 Flash
70.1
gpt-oss-20b (free)
20.7
Artificial Analysis · Quality Index
Gemini 3.5 Flash leads by +35.3
Gemini 3.5 Flash
50.2
gpt-oss-20b (free)
14.9
Full benchmark table
| Benchmark | Gemini 3.5 Flash | gpt-oss-20b (free) |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 37.5 | 3.1 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 70.1 | 20.7 |
Artificial Analysis · Quality Index | 50.2 | 14.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.50 | $9.00 | 1.0M tokens (~524 books) | $33.75 | |
| $0.00 | $0.00 | 131K tokens (~66 books) | — |
People also compared
Claude Fable 5 vs gpt-oss-20b (free)gpt-oss-20b (free) vs phi-3-small 7.4Bgpt-oss-20b (free) vs Qwen3 30B A3B Thinking 2507gpt-oss-20b (free) vs Grok 3 Mini BetaGemini 2.0 Flash Lite vs Gemini 3.5 FlashGemini 3.5 Flash vs Gemini 3.7 FlashGemini 3.5 Flash vs Gemini 3.8 FlashGemini 3.5 Flash vs Gemini 3 Pro