Model comparison
GLM-4.6 vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 41.4 on the Noometry Index. GLM-4.6 costs 2.4× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GLM-4.6 scores higher in 3 categories and Qwen3 Max in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 40.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 72.5% for Qwen3 Max.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Qwen3 Max | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 43.7 |
| Released | 2025-09-30 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 205K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.60 | $1.20 |
| Output $ / M tokens | $2.20 | $6 |
| Results tracked | 29 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
GLM-4.6: 40.1 (#148), Qwen3 Max: 43.0 (#93)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1449 | 1456 |
| ALE-Bench | 340.82 | 370.45 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), Qwen3 Max: —
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), Qwen3 Max: 22.6 (#190)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 72.5% |
| LMArena Hard Prompts | 1440 | 1448 |
| NYT Connections (extended) | — | 30.1% |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
| Epoch Capabilities Index | — | 142.38 |
Math Too close to call
GLM-4.6: 39.1 (#111), Qwen3 Max: 38.7 (#131)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| LMArena Math | 1432 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| MATH Level 5 | — | 97.1% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3 Max leads
GLM-4.6: 40.2 (#124), Qwen3 Max: 48.1 (#78)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1431 | 1455 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual Too close to call
GLM-4.6: 53.5 (#66), Qwen3 Max: 53.7 (#62)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1426 | 1429 |
| LMArena Chinese | 1499 | 1478 |
| LMArena French | 1459 | 1449 |
| LMArena German | 1447 | 1463 |
| LMArena Japanese | 1393 | 1397 |
| LMArena Korean | 1400 | 1399 |
| LMArena Russian | 1419 | 1428 |
| LMArena Spanish | 1436 | 1462 |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), Qwen3 Max: 74.8 (#87)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1410 | 1419 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), Qwen3 Max: 41.6 (#134)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1422 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
GLM-4.6: 61.1 (#90), Qwen3 Max: 62.4 (#76)
| Benchmark | GLM-4.6 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1440 | 1439 |
| LMArena Creative Writing | 1411 | 1402 |
| LMArena Multi-Turn | 1427 | 1446 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 41.4 on the Noometry Index. GLM-4.6 costs 2.4× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or Qwen3 Max?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is GLM-4.6 or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 205K.
How many benchmarks do GLM-4.6 and Qwen3 Max share?
19 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen3 Max has 33.