# GLM-5.1 vs Qwen3.7 Plus

> GLM-5.1 is the stronger model overall, scoring 47.6 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 3.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GLM-5.1 scores higher in 7 categories and Qwen3.7 Plus in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5.1 leads 48.5 to 36.1.
- The biggest single-benchmark swing is Chess Puzzles: 19% for GLM-5.1 and 24% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Qwen3.7 Plus accepts more context: 1M tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.6 | 45.0 |
| Rank | 51 | 66 |
| Context | 200K | 1M |
| Input $/M | $1.40 | $0.40 |
| Output $/M | $4.40 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.5 (#52)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| SciCode | 43.8% | 45.5% |
| LMArena Coding | 1486 | 1473 |
| SWE-bench Verified | 74.2% | — |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1509 | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| APEX-Agents | 40.9% | — |
| OSWorld 2.0 | — | 2.8% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 77.7% | 74.8% |
| CritPt | 4.6% | 9.1% |
| Chess Puzzles | 19% | 24% |
| LMArena Hard Prompts | 1472 | 1460 |
| Epoch Capabilities Index | 149.86 | 147.39 |
| SimpleBench | 55.1% | — |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |

## Math

- GLM-5.1: 49.0 (#48)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 34.4% |
| OTIS Mock AIME 2024-2025 | 93.3% | 93.3% |
| LMArena Math | 1472 | 1467 |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 89.9% | 87.9% |
| LMArena Expert | 1477 | 1467 |
| SimpleQA Verified | 34% | — |

## Multimodal

- GLM-5.1: —
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1448 | 1445 |
| LMArena Chinese | 1516 | 1510 |
| LMArena French | 1478 | 1471 |
| LMArena German | 1466 | 1471 |
| LMArena Japanese | 1436 | 1411 |
| LMArena Korean | 1423 | 1416 |
| LMArena Russian | 1453 | 1457 |
| LMArena Spanish | 1467 | 1453 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1451 | 1439 |

## Long Context

- GLM-5.1: 44.9 (#51)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1467 | 1454 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | GLM-5.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1462 | 1454 |
| LMArena Creative Writing | 1454 | 1439 |
| LMArena Multi-Turn | 1473 | 1459 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Qwen3.7 Plus?

GLM-5.1 is the stronger model overall, scoring 47.6 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 3.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.1 or Qwen3.7 Plus?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Qwen3.7 Plus better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 36.1 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 200K.

### How many benchmarks do GLM-5.1 and Qwen3.7 Plus share?

25 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3.7 Plus has 32.