# Gemini 3.6 Flash vs Qwen2-72B

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.6 Flash leads 67.8 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 94.1% for Gemini 3.6 Flash and 40.8% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 54.1 | 29.5 |
| Rank | 30 | 294 |
| Context | 1.05M | — |
| Input $/M | $0.75 | — |
| Output $/M | $3.75 | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.6 Flash: 49.6 (#45)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| WeirdML | 56.1% | 11.3% |
| LMArena Coding | 1492 | 1196 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| LMArena WebDev | 1536 | — |
| SciCode | 52.7% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 715.52 | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.4 (#56)
- Qwen2-72B: 16.9 (#138)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| APEX-Agents | 46.9% | — |
| TheAgentCompany | — | 1.1% |
| GDP.pdf | 14% | — |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Gemini 3.6 Flash: 58.9 (#20)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1486 | 1191 |
| Epoch Capabilities Index | 154.36 | 125.27 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 89% | — |
| ARC-AGI-1 | 91.2% | — |
| CritPt | 10.6% | — |
| Chess Puzzles | 43% | — |
| Mystery Game Puzzles | 30% | — |
| DTBench | 95.5% | — |
| LMCA | 44.9% | — |

## Math

- Gemini 3.6 Flash: 57.0 (#33)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| LMArena Math | 1504 | 1235 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| OTIS Mock AIME 2024-2025 | 94.2% | — |
| ProofBench | 36% | — |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#7)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 94.1% | 40.8% |
| LMArena Expert | 1489 | 1171 |
| SimpleQA Verified | 66.2% | — |
| MMLU | — | 82.4% |

## Multimodal

- Gemini 3.6 Flash: 38.7 (#55)
- Qwen2-72B: —

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1297 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.8 (#17)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1470 | 1176 |
| LMArena Chinese | 1530 | 1240 |
| LMArena French | 1501 | 1169 |
| LMArena German | 1478 | 1151 |
| LMArena Japanese | 1477 | 1111 |
| LMArena Korean | 1435 | 1083 |
| LMArena Russian | 1490 | 1169 |
| LMArena Spanish | 1477 | 1168 |

## Instruction Following

- Gemini 3.6 Flash: 77.2 (#27)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1467 | 1181 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#47)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1475 | 1193 |

## Writing & Preference

- Gemini 3.6 Flash: 68.3 (#26)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Gemini 3.6 Flash | Qwen2-72B |
|---|---|---|
| LMArena Text | 1478 | 1203 |
| LMArena Creative Writing | 1464 | 1181 |
| LMArena Multi-Turn | 1481 | 1195 |
| EQ-Bench Creative Writing | 1604 | — |

## FAQ

### Is Gemini 3.6 Flash better than Qwen2-72B?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 29.5 on the Noometry Index.

### Is Gemini 3.6 Flash or Qwen2-72B better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 28.7 in the Noometry coding category.

### How many benchmarks do Gemini 3.6 Flash and Qwen2-72B share?

20 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Qwen2-72B has 26.