# Gemini 3.7 Flash vs Qwen2.5 72B Instruct

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-7-flash-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.7 Flash leads 69.6 to 19.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Gemini 3.7 Flash and 8.1% for Qwen2.5 72B Instruct.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 59.8 | 31.9 |
| Rank | 14 | 267 |
| Context | 1.05M | 131K |
| Input $/M | $0.75 | $1.40 |
| Output $/M | $3.75 | $5.60 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.7 Flash: 56.2 (#22)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1497 | 1292 |
| DeepSWE | 65.5% | — |
| FrontierCode | 43.6% | — |
| LMArena WebDev | 1592 | — |
| FrontierSWE | 20.3% | — |
| SciCode | 59.8% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 904.3 | — |

## Agentic & Tool Use

- Gemini 3.7 Flash: 42.1 (#19)
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| APEX-Agents | 67.8% | — |
| Remote Labor Index | 5% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| GDP.pdf | 23.8% | — |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Gemini 3.7 Flash: 70.0 (#15)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1494 | 1271 |
| DTBench | 96.8% | 62.9% |
| LMCA | 50.4% | 13.4% |
| Epoch Capabilities Index | 157.27 | 129 |
| ARC-AGI-2 | 84.6% | — |
| NYT Connections (extended) | 94% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 14.3% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 37% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Gemini 3.7 Flash: 69.6 (#23)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 8.1% |
| LMArena Math | 1507 | 1283 |
| FrontierMath (Tiers 1-3) | 71.6% | — |
| FrontierMath Tier 4 | 36.6% | — |
| ProofBench | 58% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Gemini 3.7 Flash: 69.7 (#5)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 94.8% | 49.1% |
| LMArena Expert | 1508 | 1245 |
| SimpleQA Verified | 69.2% | — |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multimodal

- Gemini 3.7 Flash: 37.3 (#73)
- Qwen2.5 72B Instruct: —

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1316 | — |
| Furniture Assembly | 26.7% | — |

## Multilingual

- Gemini 3.7 Flash: 57.6 (#7)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1484 | 1252 |
| LMArena Chinese | 1548 | 1272 |
| LMArena French | 1505 | 1280 |
| LMArena German | 1498 | 1234 |
| LMArena Japanese | 1512 | 1180 |
| LMArena Korean | 1483 | 1188 |
| LMArena Russian | 1516 | 1264 |
| LMArena Spanish | 1503 | 1256 |

## Instruction Following

- Gemini 3.7 Flash: 77.7 (#15)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1483 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Gemini 3.7 Flash: 45.7 (#30)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1492 | 1282 |

## Writing & Preference

- Gemini 3.7 Flash: 71.2 (#20)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Gemini 3.7 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1486 | 1269 |
| LMArena Creative Writing | 1490 | 1221 |
| LMArena Multi-Turn | 1489 | 1272 |
| EQ-Bench Creative Writing | 1723 | — |
| WildBench | — | 80.2% |

## FAQ

### Is Gemini 3.7 Flash better than Qwen2.5 72B Instruct?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 31.9 on the Noometry Index.

### Which is cheaper, Gemini 3.7 Flash or Qwen2.5 72B Instruct?

Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is Gemini 3.7 Flash or Qwen2.5 72B Instruct better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 3.7 Flash and Qwen2.5 72B Instruct share?

22 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Qwen2.5 72B Instruct has 43.