Gemini 3.1 Flash Lite Preview
Google · released Mar 3, 2026
Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...
Specification
- Context window
- 1.05M
- Max output
- 66K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
15.6
59th percentile
Coding
34.7
Coding Index
Agentic
1.6
Agentic Index
Output speed
182 t/s
Median across providers
Latency
430ms
Time to first token
Cost per task
$0.13
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond82.2%
- IFBench77.2%
- AA-LCR (long context)74.3%
- SciCode43.4%
- τ²-bench (Telecom)31.3%
- Terminal-Bench Hard24.2%
- Humanity's Last Exam17.2%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 82.2% |
| IFBench | 77.2% |
| AA-LCR (long context) | 74.3% |
| SciCode | 43.4% |
| τ²-bench (Telecom) | 31.3% |
| Terminal-Bench Hard | 24.2% |
| Humanity's Last Exam | 17.2% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- V3.2DeepSeek16.0
- Gemini 3.1 Flash Lite PreviewGoogle15.6
- Gemini 3.1 Flash LiteGoogle15.6
- 15.6
- Claude Haiku 4.5Anthropic15.4
- Kimi K2 0905Moonshot AI15.3
- gpt-oss-20b (free)OpenAI15.2
- o1OpenAI15.2
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| V3.2 | 16.0 |
| Gemini 3.1 Flash Lite Preview | 15.6 |
| Gemini 3.1 Flash Lite | 15.6 |
| Qwen3.5-122B-A10B | 15.6 |
| Claude Haiku 4.5 | 15.4 |
| Kimi K2 0905 | 15.3 |
| gpt-oss-20b (free) | 15.2 |
| o1 | 15.2 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.25
- Output / 1M tokens
- $1.5
- Cached input / 1M
- $0.025
- Blended 3:1
- $0.563
One task, estimated
$0.13
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,084
- Win rate
- 36.6%
- Strongest at
- Websites
- Tournaments
- 13,750
Elo by category
Dot position on a 1,025–1,100 scale · Elo has no meaningful zero
- 1,084
- 1,073
- 1,050
- 1,048
- 1,045
- 1,032
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Websites | 1084 | 36.6% |
| UI components | 1073 | 37.7% |
| SVG | 1050 | 42.5% |
| 3D scenes | 1048 | 38.8% |
| Data visualisation | 1045 | 33.3% |
| Game development | 1032 | 33.7% |