# Gemini 2.5 Flash-Lite vs Gemini 3 Flash Preview

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 6.4× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-gemini-3-flash-preview
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 0 categories and Gemini 3 Flash Preview in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 21.5.
- The biggest single-benchmark swing is VPCT: 30% for Gemini 2.5 Flash-Lite and 72.6% for Gemini 3 Flash Preview.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.

## Snapshot

| | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 36.4 | 52.3 |
| Rank | 208 | 33 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.10 | $0.50 |
| Output $/M | $0.40 | $3 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash-Lite: 38.0 (#167)
- Gemini 3 Flash Preview: 51.5 (#35)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| WeirdML | 35.2% | 61.6% |
| LMArena Coding | 1373 | 1460 |
| ALE-Bench | 325.9 | 1,367 |
| SWE-bench Verified | — | 75.4% |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| GSO | — | 9.8% |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 27.8 (#89)
- Gemini 3 Flash Preview: 38.6 (#27)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | — | 64.3% |
| Berkeley Function Calling Leaderboard | 36.9% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| Vending-Bench 2 | — | 3,635 |

## Reasoning

- Gemini 2.5 Flash-Lite: 21.5 (#196)
- Gemini 3 Flash Preview: 49.2 (#35)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1465 |
| DTBench | 62.8% | 89.1% |
| LMCA | 18.1% | 43.1% |
| Epoch Capabilities Index | 133.93 | 151.83 |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 83.1% |
| ARC-AGI-1 | — | 84.7% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 26% |
| ForecastBench | — | 58.5 |

## Math

- Gemini 2.5 Flash-Lite: 35.5 (#144)
- Gemini 3 Flash Preview: 51.4 (#42)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Math | 1373 | 1472 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 15% |
| Omni-MATH | 48% | — |
| FrontierMath (Feb 2025 set) | — | 35.6% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.1 (#206)
- Gemini 3 Flash Preview: 58.8 (#30)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 13.5% |
| LMArena Expert | 1373 | 1461 |
| GPQA Diamond | — | 89.4% |
| SimpleQA Verified | — | 66.8% |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 28.6 (#109)
- Gemini 3 Flash Preview: 45.3 (#15)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | 1198 | 1285 |
| VPCT | 30% | 72.6% |
| GeoBench | — | 88% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.5 (#129)
- Gemini 3 Flash Preview: 55.9 (#26)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1369 | 1458 |
| LMArena Chinese | 1404 | 1510 |
| LMArena French | 1388 | 1478 |
| LMArena German | 1390 | 1497 |
| LMArena Japanese | 1359 | 1488 |
| LMArena Korean | 1358 | 1443 |
| LMArena Russian | 1373 | 1480 |
| LMArena Spanish | 1396 | 1470 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.2 (#163)
- Gemini 3 Flash Preview: 75.8 (#52)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1366 | 1437 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#257)
- Gemini 3 Flash Preview: 44.4 (#63)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1373 | 1452 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 57.0 (#130)
- Gemini 3 Flash Preview: 65.6 (#44)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1379 | 1466 |
| LMArena Creative Writing | 1366 | 1457 |
| LMArena Multi-Turn | 1367 | 1471 |
| WildBench | 81.8% | — |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 6.4× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash-Lite or Gemini 3 Flash Preview?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

### Is Gemini 2.5 Flash-Lite or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 38.0 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1.05M tokens.

### How many benchmarks do Gemini 2.5 Flash-Lite and Gemini 3 Flash Preview share?

25 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Gemini 3 Flash Preview has 59.