Model comparison
GLM-4.6 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 41.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and Qwen3.5 Max Preview in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 30.8 to 23.7.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 45.3 |
| Released | 2025-09-30 | — |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
GLM-4.6: 40.1 (#148), Qwen3.5 Max Preview: 44.0 (#77)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1449 | 1487 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), Qwen3.5 Max Preview: —
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Qwen3.5 Max Preview leads
GLM-4.6: 23.7 (#172), Qwen3.5 Max Preview: 30.8 (#84)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1483 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
Math Too close to call
GLM-4.6: 39.1 (#111), Qwen3.5 Max Preview: 40.1 (#94)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1432 | 1474 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.5 Max Preview leads
GLM-4.6: 40.2 (#124), Qwen3.5 Max Preview: 41.8 (#107)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1431 | 1489 |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual Qwen3.5 Max Preview leads
GLM-4.6: 53.5 (#66), Qwen3.5 Max Preview: 56.2 (#22)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1426 | 1465 |
| LMArena Chinese | 1499 | 1534 |
| LMArena French | 1459 | 1484 |
| LMArena German | 1447 | 1487 |
| LMArena Japanese | 1393 | 1495 |
| LMArena Korean | 1400 | 1438 |
| LMArena Russian | 1419 | 1471 |
| LMArena Spanish | 1436 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
GLM-4.6: 74.3 (#98), Qwen3.5 Max Preview: 77.0 (#31)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1410 | 1467 |
Long Context Qwen3.5 Max Preview leads
GLM-4.6: 43.4 (#94), Qwen3.5 Max Preview: 45.2 (#45)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1422 | 1476 |
Writing & Preference Qwen3.5 Max Preview leads
GLM-4.6: 61.1 (#90), Qwen3.5 Max Preview: 66.0 (#41)
| Benchmark | GLM-4.6 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1440 | 1470 |
| LMArena Creative Writing | 1411 | 1464 |
| LMArena Multi-Turn | 1427 | 1478 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 41.4 on the Noometry Index.
Is GLM-4.6 or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 44.0 versus 40.1 in the Noometry coding category.
How many benchmarks do GLM-4.6 and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen3.5 Max Preview has 17.