# GLM-5.1 vs Qwen3 Max

> GLM-5.1 is the stronger model overall, scoring 47.8 to 43.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-qwen3-max
- Last updated: 2026-10-11
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Qwen3 Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 22.6.
- The biggest single-benchmark swing is NYT Connections (extended): 77.7% for GLM-5.1 and 30.1% for Qwen3 Max.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | Qwen3 Max |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.8 | 43.7 |
| Rank | 59 | 87 |
| Context | 200K | 262K |
| Input $/M | $1.40 | $1.20 |
| Output $/M | $4.40 | $6 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.7 (#55)
- Qwen3 Max: 43.0 (#93)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1485 | 1456 |
| ALE-Bench | 887.1 | 370.45 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Qwen3 Max: —

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | 5,634 | 71.56 |
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Qwen3 Max: 22.6 (#190)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 77.7% | 30.1% |
| Chess Puzzles | 19% | 4% |
| LMArena Hard Prompts | 1472 | 1448 |
| Epoch Capabilities Index | 149.84 | 142.38 |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 72.5% |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |

## Math

- GLM-5.1: 49.7 (#60)
- Qwen3 Max: 38.7 (#131)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 18.9% |
| OTIS Mock AIME 2024-2025 | 93.3% | 73.3% |
| LMArena Math | 1473 | 1446 |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 97.1% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Qwen3 Max: 48.1 (#78)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 89.9% | 72.6% |
| SimpleQA Verified | 34% | 48.7% |
| LMArena Expert | 1476 | 1455 |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Qwen3 Max: 53.7 (#62)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1447 | 1429 |
| LMArena Chinese | 1515 | 1478 |
| LMArena French | 1474 | 1449 |
| LMArena German | 1465 | 1463 |
| LMArena Japanese | 1434 | 1397 |
| LMArena Korean | 1418 | 1399 |
| LMArena Russian | 1454 | 1428 |
| LMArena Spanish | 1469 | 1462 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Qwen3 Max: 74.8 (#87)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1451 | 1419 |

## Long Context

- GLM-5.1: 44.9 (#53)
- Qwen3 Max: 41.6 (#134)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1466 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Qwen3 Max: 62.4 (#76)

| Benchmark | GLM-5.1 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1461 | 1439 |
| LMArena Creative Writing | 1453 | 1402 |
| LMArena Multi-Turn | 1472 | 1446 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Qwen3 Max?

GLM-5.1 is the stronger model overall, scoring 47.8 to 43.7 on the Noometry Index.

### Which is cheaper, GLM-5.1 or Qwen3 Max?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Qwen3 Max lists at $1.20 and $6.

### Is GLM-5.1 or Qwen3 Max better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 43.0 in the Noometry coding category.

### Which has the bigger context window?

Qwen3 Max does, with 262K tokens against 200K.

### How many benchmarks do GLM-5.1 and Qwen3 Max share?

26 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3 Max has 33.