Gemini 3.1 Flash-Lite vs Gemini 3.5 Flash-Lite
| Spec | Gemini 3.1 Flash-Lite | Gemini 3.5 Flash-Lite |
|---|---|---|
| Respan Index | 26.9 (#102) | 29.9 (#93) |
| Blended price per 1M | $0.563 | $0.85 |
| Context window | 1.0M | 1.0M |
| Input / output per 1M | $0.25 / $1.5 | $0.3 / $2.5 |
| Max output | 66K | 66K |
| Input | text, vision, audio | text, vision, audio |
| Released | 2026-03-03 | 2026-07-21 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Gemini 3.1 Flash-Lite | Gemini 3.5 Flash-Lite |
|---|---|---|
| Coding | 9.4 Gemini 3.1 Flash-Lite | 6.0 Gemini 3.5 Flash-Lite |
| Agents | 26.6* Gemini 3.1 Flash-Lite | 44.0 Gemini 3.5 Flash-Lite |
| Reasoning | 29.6 Gemini 3.1 Flash-Lite | 25.6 Gemini 3.5 Flash-Lite |
| Knowledge & language | 34.1 Gemini 3.1 Flash-Lite | 32.0 Gemini 3.5 Flash-Lite |
| Human preference | 47.5 Gemini 3.1 Flash-Lite | 52.0 Gemini 3.5 Flash-Lite |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
Gemini 3.1 Flash-Lite leads on 6 of the 9 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Gemini 3.1 Flash-Lite | Gemini 3.5 Flash-Lite |
|---|---|---|
| LMArena Elo | 1433 | 1455 |
| LMArena Vision (LMArena) | 1234 | 1266 |
| LMArena WebDev (LMArena) | 1256 | 1432 |
| Chess Puzzles (Epoch AI) | 25% | 21% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 27.7% | 26% |
| GPQA Diamond | 86.9% | 83.3% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 80% | 71.1% |
| SAGE (Vals AI) | 49.5% | 47.3% |
| WeirdML (Håvard Tveit Ihle) | 52.2% | 39% |
FAQ
Is Gemini 3.1 Flash-Lite better than Gemini 3.5 Flash-Lite?
Gemini 3.5 Flash-Lite scores 29.9 on the Respan Index (#93), ahead of Gemini 3.1 Flash-Lite at 26.9 (#102). Gemini 3.1 Flash-Lite leads on 6 of the 9 benchmarks both report.
Which is cheaper, Gemini 3.1 Flash-Lite or Gemini 3.5 Flash-Lite?
Gemini 3.1 Flash-Lite lists at $0.25 input and $1.5 output per 1M tokens; Gemini 3.5 Flash-Lite at $0.3 and $2.5. Gemini 3.1 Flash-Lite is 1.5x cheaper per token at list price.
Which has the larger context window?
Both accept 1.0M tokens of context.