Gemini 3.1 Flash Lite
46.4#186 of 427 overall
- Input / output
- US$ 0,25 / US$ 1,50 US$ per 1M tokens
- Context
- 1.0M tokens
- Release
- 05/07/2026 release date
- Weights
- Closed
- Speed
- 0 tok/s first token in 0.00 s
Family history
The 4 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | AA Intel. | Elo Arena |
|---|---|---|---|---|---|
| Gemini 2.0 Flash-Lite | 02/05/2025 | 24.4 | #393 | — | 1330 |
| Gemini 2.5 Flash Lite | 07/22/2025 | 41.0 | #249 | — | 1379 |
| Gemini 3.1 Flash Lite | 05/07/2026 | 46.4 | #186 | — | 1416 |
| Gemini 3.5 Flash Lite | 07/21/2026 | 44.2 | #205 | 11.7 | 1435 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1416 | 53% | LMArena |
| Arena WebDev (Elo) weight 1 | 1256 | 11% | LMArena |
| Arena vision (Elo) weight 0.5 | 1240 | 43% | LMArena |
| Humanity's Last Exam weight 1 | 17.2 | 65% | Artificial Analysis |
| Terminal-Bench weight 1 | 0.5 | 49% | Artificial Analysis |
| GPQA Diamond | 82.2 | 71% | Artificial Analysis |
| Long-context reasoning | 74.3 | 72% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 49.3 | #73 | Terminal-Bench |
| Coding | 30.4 | #107 | Arena WebDev (Elo) |
| Reasoning | 62.2 | #129 | Humanity's Last Exam, GPQA Diamond |
| Research | 61.0 | #92 | Long-context reasoning |
| Design | 30.4 | #105 | Arena WebDev (Elo) |
| Chat | 51.3 | #94 | Arena text (Elo) |
| Vision | 46.6 | #61 | Arena vision (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.