ModelsGemini 3.8 Flash
Gemini 3.8 Flash
Google’s Gemini 3.8 Flash model for multimodal reasoning and tool use.
- Context window
- 1M tokens
- Maximum output
- 66k tokens
- Input / output
- $0.75 / $3.75USD per million tokens
- Tests with results
- 5062 source-specific results
- AA Intelligence Index
- 41.00Evaluator composite, own scale
Test coverage
- 16aa
- 1arc prize · standard
- 2scale ai / seal
- 29vals
- 1datacurve
- 1self
- 115 no result
165 catalogue tests. Each test counts once; evaluator results take precedence where sources overlap.
Results
Filter the recorded results; open Details on a row for run conditions.
62 results
| Benchmark | Result | Source | Run |
|---|---|---|---|
| τ³-Banking | 44.95% | aa | DetailsHighest published effort per model release, grouped here from AA’s public results. Grouping ranks are derived here; source settings and model-publisher reports stay separate.
|
| ITBench-AA | 52.54% | aa | DetailsHighest published effort per model release, grouped here from AA’s public results. Grouping ranks are derived here; source settings and model-publisher reports stay separate.
|
| MLCR-AA | 21.67% | aa | DetailsHighest published effort per model release, grouped here from AA’s public results. Grouping ranks are derived here; source settings and model-publisher reports stay separate.
|
| ARC-AGI-3 | 10.37%· Standard | arc prize · standard | DetailsVerified semi-private set; best published configuration per release within this scaffold. Public demo and community submissions excluded. Standard and adapter results remain separate.
|
| 35.00%· Provider adapter | arc prize · provider adapter | DetailsVerified semi-private set; best published configuration per release within this scaffold. Public demo and community submissions excluded. Standard and adapter results remain separate.
| |
| SWE-Bench Pro V2 Full | 94.86% | scale ai / seal | DetailsV2 FULL field, as published. Different agent scaffolds and effort settings are retained per row; this is a model-and-agent comparison.
|
| SWE-Bench Pro V2 HARD | 58.80% | scale ai / seal | DetailsV2 HARD field, as published. Different agent scaffolds and effort settings are retained per row; this is a model-and-agent comparison.
|
| Vals RSI Index | 19.93% | vals | DetailsCan a model do the research that builds the next model? Autonomous LLM R&D scored against frozen published, human, and frontier-model references.
|
| Vibe Code Bench 1–100 | 18.77% | vals | DetailsCan models extend a working web application across a long sequence of dependent requests?
|
| CUA-bench | 4.17% | vals | DetailsCan an AI agent play six commercial video games with only a keyboard and a mouse? Half of them are held out.
|
| AutomationBench-AA | 59.93% | aa | DetailsHighest published effort per model release, grouped here from AA’s public results. Grouping ranks are derived here; source settings and model-publisher reports stay separate.
|
| SciCode | 56.60% | aa | DetailsHighest published effort per model release, grouped here from AA’s public results. Grouping ranks are derived here; source settings and model-publisher reports stay separate.
|
| GDP.pdf | 21.00% | aa | DetailsHighest published effort per model release, grouped here from AA’s public results. Grouping ranks are derived here; source settings and model-publisher reports stay separate.
|
API & pricing
Open one section for prompt tiers, runtime rates, endpoint measurements and effort configurations.
Published pricing, runtime and evaluator details
Current pricing
The listed $0.75 input / $3.75 output price applies through 31 December 2026. Google lists $1.50 / $7.50 from 1 January 2027.
Read source ↗Documentation read 30 September 2026.
No separate hosted-runtime record was checked for this release.
AA API performance and evaluation cost
- Output speed
- 238.736904635898 tokens/s
- First answer token
- 20.7603934870001 seconds
- 500-token response
- 22.854749199463406 seconds
- Index cost per task
- $1.2427947606950427
Artificial Analysis endpoint measurements. Provider, effort and snapshot may differ from the official API specifications.
Evaluator source ↗