Model comparison
GLM-4.6 vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 41.4 on the Noometry Index. GLM-4.6 costs 3.8× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. GLM-4.6 scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 49.2 to 23.7.
- The biggest single-benchmark swing is CritPt: 1.1% for GLM-4.6 and 13.4% for Qwen3.7 Max.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Qwen3.7 Max | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 51.5 |
| Released | 2025-09-30 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.60 | $2.50 |
| Output $ / M tokens | $2.20 | $7.50 |
| Results tracked | 29 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
GLM-4.6: 40.1 (#148), Qwen3.7 Max: 50.4 (#45)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1340 | 1515 |
| SciCode | 38.4% | 48.8% |
| LMArena Coding | 1449 | 1498 |
| ALE-Bench | 340.82 | 1,189 |
| SWE-bench Verified | — | 77.3% |
| SWE-bench Verified (bash only) | 55.4% | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), Qwen3.7 Max: 22.1 (#135)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
GLM-4.6: 23.7 (#172), Qwen3.7 Max: 49.2 (#38)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| CritPt | 1.1% | 13.4% |
| LMArena Hard Prompts | 1440 | 1483 |
| SimpleBench | — | 70.4% |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 85.1% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.68 |
Math Qwen3.7 Max leads
GLM-4.6: 39.1 (#111), Qwen3.7 Max: 62.4 (#32)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1432 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.7 Max leads
GLM-4.6: 40.2 (#124), Qwen3.7 Max: 61.6 (#28)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1431 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual Qwen3.7 Max leads
GLM-4.6: 53.5 (#66), Qwen3.7 Max: 56.9 (#15)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1426 | 1474 |
| LMArena Chinese | 1499 | 1530 |
| LMArena Russian | 1419 | 1484 |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1393 | — |
| LMArena Korean | 1400 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Qwen3.7 Max leads
GLM-4.6: 74.3 (#98), Qwen3.7 Max: 76.7 (#38)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1410 | 1460 |
Long Context Qwen3.7 Max leads
GLM-4.6: 43.4 (#94), Qwen3.7 Max: 45.4 (#40)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1422 | 1482 |
Writing & Preference Qwen3.7 Max leads
GLM-4.6: 61.1 (#90), Qwen3.7 Max: 65.0 (#54)
| Benchmark | GLM-4.6 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1440 | 1476 |
| LMArena Creative Writing | 1411 | 1449 |
| LMArena Multi-Turn | 1427 | 1481 |
| EQ-Bench Creative Writing | 1411 | — |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is GLM-4.6 better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 41.4 on the Noometry Index. GLM-4.6 costs 3.8× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or Qwen3.7 Max?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is GLM-4.6 or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 205K.
How many benchmarks do GLM-4.6 and Qwen3.7 Max share?
16 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen3.7 Max has 33.