# Qwen3.7 Plus vs Qwen3.8 27B

> Qwen3.7 Plus and Qwen3.8 27B score almost the same on the Noometry Index (45.3 vs 46.0), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/qwen3-7-plus-vs-qwen3-8-27b
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Qwen3.7 Plus scores higher in 6 categories and Qwen3.8 27B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3.8 27B leads 50.5 to 36.6.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for Qwen3.7 Plus and 54.5% for Qwen3.8 27B.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.99 / $1.49 for Qwen3.8 27B.
- Qwen3.7 Plus accepts more context: 1M tokens versus 262K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 45.3 | 46.0 |
| Rank | 72 | 68 |
| Context | 1M | 262K |
| Input $/M | $0.40 | $0.99 |
| Output $/M | $1.60 | $1.49 |
| Weights | Proprietary | Open |

## Coding

- Qwen3.7 Plus: 36.6 (#206)
- Qwen3.8 27B: 50.5 (#44)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| SciCode | 45.5% | 46.6% |
| LMArena Coding | 1473 | 1482 |
| FrontierCode | 10.2% | — |
| LMArena WebDev | — | 1593 |

## Agentic & Tool Use

- Qwen3.7 Plus: 21.4 (#138)
- Qwen3.8 27B: 32.9 (#57)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
| OSWorld 2.0 | 2.8% | — |

## Reasoning

- Qwen3.7 Plus: 39.3 (#59)
- Qwen3.8 27B: 41.0 (#54)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| NYT Connections (extended) | 74.8% | 54.5% |
| CritPt | 9.1% | 5.4% |
| LMArena Hard Prompts | 1460 | 1460 |
| DTBench | 84% | 88% |
| LMCA | 37.6% | 41.4% |
| Epoch Capabilities Index | 147.37 | 149.38 |
| ARC-AGI-2 | — | 42.4% |
| ARC-AGI-1 | — | 87.5% |
| Chess Puzzles | 24% | — |
| Mystery Game Puzzles | 17% | — |
| Surface Evolver Bench | — | 45% |

## Math

- Qwen3.7 Plus: 50.5 (#56)
- Qwen3.8 27B: 37.1 (#161)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1466 | 1456 |
| FrontierMath (Tiers 1-3) | 34.4% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | — | 16% |

## Knowledge

- Qwen3.7 Plus: 54.9 (#51)
- Qwen3.8 27B: 41.6 (#109)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1467 | 1482 |
| GPQA Diamond | 87.9% | — |

## Multimodal

- Qwen3.7 Plus: 41.8 (#33)
- Qwen3.8 27B: 41.3 (#37)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | 1279 | 1271 |
| LMArena Document | 1444 | — |

## Multilingual

- Qwen3.7 Plus: 54.8 (#38)
- Qwen3.8 27B: 53.7 (#60)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1445 | 1430 |
| LMArena Chinese | 1510 | 1504 |
| LMArena French | 1473 | 1465 |
| LMArena German | 1471 | 1438 |
| LMArena Japanese | 1413 | 1384 |
| LMArena Korean | 1415 | 1393 |
| LMArena Russian | 1457 | 1415 |
| LMArena Spanish | 1457 | 1448 |

## Instruction Following

- Qwen3.7 Plus: 75.8 (#52)
- Qwen3.8 27B: 75.8 (#53)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1440 | 1439 |

## Long Context

- Qwen3.7 Plus: 44.5 (#65)
- Qwen3.8 27B: 44.3 (#70)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1455 | 1450 |

## Writing & Preference

- Qwen3.7 Plus: 64.3 (#56)
- Qwen3.8 27B: 65.8 (#43)

| Benchmark | Qwen3.7 Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1455 | 1441 |
| LMArena Creative Writing | 1439 | 1384 |
| LMArena Multi-Turn | 1460 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |

## FAQ

### Is Qwen3.7 Plus better than Qwen3.8 27B?

Qwen3.7 Plus and Qwen3.8 27B score almost the same on the Noometry Index (45.3 vs 46.0), so choose on price, context window or the category you care about most.

### Which is cheaper, Qwen3.7 Plus or Qwen3.8 27B?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Qwen3.8 27B lists at $0.99 and $1.49.

### Is Qwen3.7 Plus or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 36.6 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 262K.

### How many benchmarks do Qwen3.7 Plus and Qwen3.8 27B share?

24 benchmarks have published results for both models. Qwen3.7 Plus has 32 scored results on Noometry and Qwen3.8 27B has 31.