# Gemini 2.5 Flash-Lite vs Gemini 3.7 Flash

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 8.6× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-gemini-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 0 categories and Gemini 3.7 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.1 to 21.5.
- The biggest single-benchmark swing is DTBench: 62.8% for Gemini 2.5 Flash-Lite and 96.8% for Gemini 3.7 Flash.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.

## Snapshot

| | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 36.4 | 59.8 |
| Rank | 208 | 11 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.10 | $0.75 |
| Output $/M | $0.40 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash-Lite: 38.0 (#167)
- Gemini 3.7 Flash: 55.7 (#19)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Coding | 1373 | 1499 |
| ALE-Bench | 325.9 | 904.3 |
| DeepSWE | — | 65.5% |
| FrontierCode | — | 43.6% |
| LMArena WebDev | — | 1593 |
| FrontierSWE | — | 20.3% |
| SciCode | — | 59.8% |
| WeirdML | 35.2% | — |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 27.8 (#89)
- Gemini 3.7 Flash: 42.2 (#18)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | — | 67.8% |
| Berkeley Function Calling Leaderboard | 36.9% | — |
| Remote Labor Index | — | 5% |
| GDP.pdf | — | 23.8% |

## Reasoning

- Gemini 2.5 Flash-Lite: 21.5 (#196)
- Gemini 3.7 Flash: 70.1 (#12)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1497 |
| DTBench | 62.8% | 96.8% |
| LMCA | 18.1% | 50.4% |
| Epoch Capabilities Index | 133.93 | 157.72 |
| ARC-AGI-2 | — | 84.6% |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 94% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 14.3% |
| Chess Puzzles | — | 47% |
| Mystery Game Puzzles | — | 37% |

## Math

- Gemini 2.5 Flash-Lite: 35.5 (#144)
- Gemini 3.7 Flash: 69.5 (#18)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Math | 1373 | 1511 |
| FrontierMath (Tiers 1-3) | — | 71.6% |
| FrontierMath Tier 4 | — | 36.6% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 58% |
| Omni-MATH | 48% | — |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.1 (#206)
- Gemini 3.7 Flash: 69.8 (#4)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Expert | 1373 | 1508 |
| GPQA Diamond | — | 94.8% |
| SimpleQA Verified | — | 69.2% |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 28.6 (#109)
- Gemini 3.7 Flash: 36.9 (#69)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1198 | 1314 |
| VPCT | 30% | — |
| Furniture Assembly | — | 26.7% |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.5 (#129)
- Gemini 3.7 Flash: 57.8 (#7)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1369 | 1485 |
| LMArena Chinese | 1404 | 1553 |
| LMArena French | 1388 | 1512 |
| LMArena German | 1390 | 1485 |
| LMArena Japanese | 1359 | 1506 |
| LMArena Korean | 1358 | 1486 |
| LMArena Russian | 1373 | 1519 |
| LMArena Spanish | 1396 | 1507 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.2 (#163)
- Gemini 3.7 Flash: 78.0 (#12)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1366 | 1486 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#257)
- Gemini 3.7 Flash: 45.8 (#28)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1373 | 1493 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 57.0 (#130)
- Gemini 3.7 Flash: 71.4 (#19)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1379 | 1487 |
| LMArena Creative Writing | 1366 | 1490 |
| LMArena Multi-Turn | 1367 | 1495 |
| EQ-Bench Creative Writing | — | 1723 |
| WildBench | 81.8% | — |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Gemini 3.7 Flash?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 8.6× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash-Lite or Gemini 3.7 Flash?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.

### Is Gemini 2.5 Flash-Lite or Gemini 3.7 Flash better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 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 3.7 Flash share?

22 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Gemini 3.7 Flash has 44.