Model comparison
GLM-4.6 vs Qwen Max
GLM-4.6 is the stronger model overall, scoring 40.9 to 34.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. GLM-4.6 scores higher in 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 36.4 to 21.0.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- GLM-4.6 accepts more context: 205K tokens versus 33K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Qwen Max | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 40.9 | 34.4 |
| Released | 2025-09-30 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 205K | 33K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.60 | $1.60 |
| Output $ / M tokens | $2.20 | $6.40 |
| Results tracked | 29 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Qwen Max: 30.3 (#288)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Coding | 1449 | 1288 |
| SWE-bench Verified (bash only) | 55.4% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1339 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.1 (#60), Qwen Max: —
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Qwen Max leads
GLM-4.6: 23.1 (#168), Qwen Max: 24.1 (#154)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1270 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
Math GLM-4.6 leads
GLM-4.6: 36.4 (#115), Qwen Max: 21.0 (#272)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Math | 1431 | 1275 |
| FrontierMath (Feb 2025 set) | 3.8% | 1% |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 39.6 (#118), Qwen Max: 30.3 (#222)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Expert | 1432 | 1248 |
| GPQA Diamond | — | 56.1% |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Qwen Max: 42.0 (#197)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1426 | 1263 |
| LMArena Chinese | 1500 | 1254 |
| LMArena French | 1459 | 1329 |
| LMArena German | 1447 | 1254 |
| LMArena Japanese | 1394 | 1205 |
| LMArena Korean | 1401 | 1141 |
| LMArena Russian | 1418 | 1274 |
| LMArena Spanish | 1436 | 1290 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.5 (#93), Qwen Max: 66.7 (#203)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1410 | 1262 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#91), Qwen Max: 39.4 (#175)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1423 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Qwen Max: 48.0 (#200)
| Benchmark | GLM-4.6 | Qwen Max |
|---|---|---|
| LMArena Text | 1440 | 1282 |
| LMArena Creative Writing | 1411 | 1248 |
| LMArena Multi-Turn | 1427 | 1277 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Qwen Max?
GLM-4.6 is the stronger model overall, scoring 40.9 to 34.4 on the Noometry Index.
Which is cheaper, GLM-4.6 or Qwen Max?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is GLM-4.6 or Qwen Max better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 33K.
How many benchmarks do GLM-4.6 and Qwen Max share?
18 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen Max has 23.