# Gemini 2.5 Flash-Lite vs Qwen2-72B

> Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 7 categories and Qwen2-72B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Flash-Lite leads 56.8 to 40.8.
- The biggest single-benchmark swing is WeirdML: 35.2% for Gemini 2.5 Flash-Lite and 11.3% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 37.0 | 30.0 |
| Rank | 211 | 300 |
| Context | 1.05M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.40 | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash-Lite: 38.5 (#173)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| WeirdML | 35.2% | 11.3% |
| LMArena Coding | 1373 | 1196 |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 325.9 | — |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 28.0 (#96)
- Qwen2-72B: 17.0 (#146)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Gemini 2.5 Flash-Lite: 22.2 (#205)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1191 |
| Epoch Capabilities Index | 133.94 | 125.28 |
| Kagi LLM Benchmark | 40.5% | — |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |

## Math

- Gemini 2.5 Flash-Lite: 38.0 (#144)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Math | 1373 | 1235 |
| Omni-MATH | 48% | — |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.5 (#210)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1373 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
| MMLU | — | 82.4% |

## Multimodal

- Gemini 2.5 Flash-Lite: 29.1 (#114)
- Qwen2-72B: —

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.3 (#134)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1369 | 1176 |
| LMArena Chinese | 1404 | 1240 |
| LMArena French | 1388 | 1170 |
| LMArena German | 1389 | 1151 |
| LMArena Japanese | 1359 | 1111 |
| LMArena Korean | 1360 | 1083 |
| LMArena Russian | 1373 | 1169 |
| LMArena Spanish | 1396 | 1169 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.0 (#168)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1367 | 1181 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#262)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1373 | 1192 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 56.8 (#135)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Gemini 2.5 Flash-Lite | Qwen2-72B |
|---|---|---|
| LMArena Text | 1379 | 1203 |
| LMArena Creative Writing | 1367 | 1181 |
| LMArena Multi-Turn | 1366 | 1196 |
| WildBench | 81.8% | — |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Qwen2-72B?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 30.0 on the Noometry Index.

### Is Gemini 2.5 Flash-Lite or Qwen2-72B better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.5 versus 29.1 in the Noometry coding category.

### How many benchmarks do Gemini 2.5 Flash-Lite and Qwen2-72B share?

19 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Qwen2-72B has 26.