# Qwen2.5 7B Instruct vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.5 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 12× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/qwen2-5-7b-instruct-vs-qwen3-7-max
- Last updated: 2026-10-12
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 1 category and Qwen3.7 Max in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.4 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Qwen2.5 7B Instruct and 95.6% for Qwen3.7 Max.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 131K.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.0 | 51.5 |
| Rank | 320 | 42 |
| Context | 131K | 1M |
| Input $/M | $0.17 | $2.50 |
| Output $/M | $0.70 | $7.50 |
| Weights | Open | Proprietary |

## Coding

- Qwen2.5 7B Instruct: 36.5 (#208)
- Qwen3.7 Max: 50.4 (#45)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1498 |
| BigCodeBench Complete | 46.1% | — |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- Qwen2.5 7B Instruct: 23.8 (#124)
- Qwen3.7 Max: 22.1 (#135)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| BALROG | 7.8% | — |
| GBAEval | — | 0.4% |

## Reasoning

- Qwen2.5 7B Instruct: 14.8 (#322)
- Qwen3.7 Max: 49.2 (#38)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| Chess Puzzles | 0% | 19% |
| DTBench | 47.7% | 92.3% |
| LMCA | 6.4% | 44% |
| Epoch Capabilities Index | 118.51 | 153.68 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| EBR-Bench | — | 9.5% |
| LMArena Hard Prompts | — | 1483 |
| Mystery Game Puzzles | — | 32% |

## Math

- Qwen2.5 7B Instruct: 12.6 (#306)
- Qwen3.7 Max: 62.4 (#32)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 95.6% |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1490 |

## Knowledge

- Qwen2.5 7B Instruct: 17.0 (#286)
- Qwen3.7 Max: 61.6 (#28)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 35.5% | 90.9% |
| SimpleQA Verified | — | 55.8% |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1488 |
| MMLU | 72.9% | — |

## Multilingual

- Qwen2.5 7B Instruct: —
- Qwen3.7 Max: 56.9 (#15)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | — | 1474 |
| LMArena Chinese | — | 1530 |
| LMArena Russian | — | 1484 |

## Instruction Following

- Qwen2.5 7B Instruct: 63.2 (#231)
- Qwen3.7 Max: 76.7 (#38)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1460 |

## Long Context

- Qwen2.5 7B Instruct: —
- Qwen3.7 Max: 45.4 (#40)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | — | 1482 |

## Writing & Preference

- Qwen2.5 7B Instruct: 48.8 (#195)
- Qwen3.7 Max: 65.0 (#54)

| Benchmark | Qwen2.5 7B Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Text | — | 1476 |
| LMArena Creative Writing | — | 1449 |
| WildBench | 73.1% | — |
| EQ-Bench 4 | — | 1110 |
| LMArena Multi-Turn | — | 1481 |

## FAQ

### Is Qwen2.5 7B Instruct better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 12× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

### Which is cheaper, Qwen2.5 7B Instruct or Qwen3.7 Max?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

### Is Qwen2.5 7B Instruct or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 36.5 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Max does, with 1M tokens against 131K.

### How many benchmarks do Qwen2.5 7B Instruct and Qwen3.7 Max share?

6 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen3.7 Max has 33.