# GLM-5.1 vs Qwen Max

> GLM-5.1 is the stronger model overall, scoring 47.6 to 34.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.0 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 16.1% for Qwen Max.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- GLM-5.1 accepts more context: 200K tokens versus 33K.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | Qwen Max |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.6 | 34.4 |
| Rank | 51 | 226 |
| Context | 200K | 33K |
| Input $/M | $1.40 | $1.60 |
| Output $/M | $4.40 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.5 (#52)
- Qwen Max: 30.3 (#288)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| LMArena Coding | 1486 | 1288 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Qwen Max: —

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Qwen Max: 24.1 (#154)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1270 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| Epoch Capabilities Index | 149.86 | — |

## Math

- GLM-5.1: 49.0 (#48)
- Qwen Max: 21.0 (#272)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 16.1% |
| LMArena Math | 1472 | 1275 |
| FrontierMath (Feb 2025 set) | 33.4% | 1% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Qwen Max: 30.3 (#222)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| GPQA Diamond | 89.9% | 56.1% |
| LMArena Expert | 1477 | 1248 |
| SimpleQA Verified | 34% | — |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Qwen Max: 42.0 (#197)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1448 | 1263 |
| LMArena Chinese | 1516 | 1254 |
| LMArena French | 1478 | 1329 |
| LMArena German | 1466 | 1254 |
| LMArena Japanese | 1436 | 1205 |
| LMArena Korean | 1423 | 1141 |
| LMArena Russian | 1453 | 1274 |
| LMArena Spanish | 1467 | 1290 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Qwen Max: 66.7 (#203)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1451 | 1262 |

## Long Context

- GLM-5.1: 44.9 (#51)
- Qwen Max: 39.4 (#175)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1467 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Qwen Max: 48.0 (#200)

| Benchmark | GLM-5.1 | Qwen Max |
|---|---|---|
| LMArena Text | 1462 | 1282 |
| LMArena Creative Writing | 1454 | 1248 |
| LMArena Multi-Turn | 1473 | 1277 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Qwen Max?

GLM-5.1 is the stronger model overall, scoring 47.6 to 34.4 on the Noometry Index.

### Which is cheaper, GLM-5.1 or Qwen Max?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is GLM-5.1 or Qwen Max better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 33K.

### How many benchmarks do GLM-5.1 and Qwen Max share?

20 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen Max has 23.