# GLM-4.6 vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.0 to 40.9 on the Noometry Index. GLM-4.6 costs 3.0× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 36.4.
- The biggest single-benchmark swing is CritPt: 1.1% for GLM-4.6 and 20% for Qwen3.8 Max.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 40.9 | 56.0 |
| Rank | 132 | 21 |
| Context | 205K | 1M |
| Input $/M | $0.60 | $2 |
| Output $/M | $2.20 | $6 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6: 39.9 (#137)
- Qwen3.8 Max: 52.3 (#30)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1339 | 1671 |
| SciCode | 38.4% | 52.9% |
| LMArena Coding | 1449 | 1499 |
| DeepSWE | — | 57.5% |
| SWE-bench Verified (bash only) | 55.4% | — |
| FrontierSWE | — | 15.8% |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- Qwen3.8 Max: 42.6 (#17)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- GLM-4.6: 23.1 (#168)
- Qwen3.8 Max: 53.4 (#26)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| CritPt | 1.1% | 20% |
| LMArena Hard Prompts | 1440 | 1493 |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 88.3% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.69 |

## Math

- GLM-4.6: 36.4 (#115)
- Qwen3.8 Max: 73.1 (#15)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1431 | 1498 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 39.6 (#118)
- Qwen3.8 Max: 61.7 (#25)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1432 | 1504 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| Vectara Hallucination Rate | 9.5% | — |

## Multimodal

- GLM-4.6: —
- Qwen3.8 Max: 36.9 (#70)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- GLM-4.6: 53.6 (#62)
- Qwen3.8 Max: 56.6 (#18)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1426 | 1468 |
| LMArena Chinese | 1500 | 1537 |
| LMArena French | 1459 | 1502 |
| LMArena German | 1447 | 1489 |
| LMArena Japanese | 1394 | 1466 |
| LMArena Korean | 1401 | 1467 |
| LMArena Russian | 1418 | 1478 |
| LMArena Spanish | 1436 | 1495 |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- Qwen3.8 Max: 77.7 (#19)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1410 | 1478 |

## Long Context

- GLM-4.6: 43.4 (#91)
- Qwen3.8 Max: 45.5 (#30)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1423 | 1486 |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- Qwen3.8 Max: 67.0 (#31)

| Benchmark | GLM-4.6 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1440 | 1480 |
| LMArena Creative Writing | 1411 | 1478 |
| LMArena Multi-Turn | 1427 | 1487 |
| EQ-Bench Creative Writing | 1411 | — |

## FAQ

### Is GLM-4.6 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 40.9 on the Noometry Index. GLM-4.6 costs 3.0× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.6 or Qwen3.8 Max?

GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen3.8 Max lists at $2 and $6.

### Is GLM-4.6 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 39.9 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 205K.

### How many benchmarks do GLM-4.6 and Qwen3.8 Max share?

20 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen3.8 Max has 38.