# Gemini 3.5 Flash Lite vs Qwen2-72B

> Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-lite-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 8 categories and Qwen2-72B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.1 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 83.3% for Gemini 3.5 Flash Lite and 40.8% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 41.5 | 30.0 |
| Rank | 133 | 300 |
| Context | 1.05M | — |
| Input $/M | $0.30 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.5 Flash Lite: 42.4 (#104)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| WeirdML | 39% | 11.3% |
| LMArena Coding | 1453 | 1196 |
| LMArena WebDev | 1440 | — |
| SciCode | 41.3% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 765.27 | — |

## Agentic & Tool Use

- Gemini 3.5 Flash Lite: 25.7 (#107)
- Qwen2-72B: 17.0 (#146)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| APEX-Agents | 29.3% | — |
| TheAgentCompany | — | 1.1% |
| GDP.pdf | 10% | — |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Gemini 3.5 Flash Lite: 27.8 (#114)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1441 | 1191 |
| Epoch Capabilities Index | 145.13 | 125.28 |
| ARC-AGI-2 | 10.3% | — |
| NYT Connections (extended) | 60.4% | — |
| ARC-AGI-1 | 53.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 22% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |

## Math

- Gemini 3.5 Flash Lite: 25.9 (#264)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| LMArena Math | 1433 | 1235 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 13% | — |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Gemini 3.5 Flash Lite: 50.1 (#72)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 83.3% | 40.8% |
| LMArena Expert | 1435 | 1171 |
| MMLU | — | 82.4% |

## Multimodal

- Gemini 3.5 Flash Lite: 41.1 (#40)
- Qwen2-72B: —

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1268 | — |

## Multilingual

- Gemini 3.5 Flash Lite: 53.5 (#63)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1427 | 1176 |
| LMArena Chinese | 1469 | 1240 |
| LMArena French | 1451 | 1170 |
| LMArena German | 1454 | 1151 |
| LMArena Japanese | 1427 | 1111 |
| LMArena Korean | 1407 | 1083 |
| LMArena Russian | 1443 | 1169 |
| LMArena Spanish | 1442 | 1169 |

## Instruction Following

- Gemini 3.5 Flash Lite: 74.8 (#85)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1181 |

## Long Context

- Gemini 3.5 Flash Lite: 43.9 (#84)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1435 | 1192 |

## Writing & Preference

- Gemini 3.5 Flash Lite: 64.2 (#57)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Gemini 3.5 Flash Lite | Qwen2-72B |
|---|---|---|
| LMArena Text | 1435 | 1203 |
| LMArena Creative Writing | 1420 | 1181 |
| LMArena Multi-Turn | 1445 | 1196 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is Gemini 3.5 Flash Lite better than Qwen2-72B?

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 30.0 on the Noometry Index.

### Is Gemini 3.5 Flash Lite or Qwen2-72B better for coding?

Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.4 versus 29.1 in the Noometry coding category.

### How many benchmarks do Gemini 3.5 Flash Lite and Qwen2-72B share?

20 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Qwen2-72B has 26.