Model comparison
GLM-4.6V vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 41.3 on the Noometry Index. GLM-4.6V costs 3.0× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. GLM-4.6V scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 38.0.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 128K.
Side by side
| GLM-4.6V | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.3 | 46.0 |
| Released | 2025-12-08 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.30 | $0.60 |
| Output $ / M tokens | $0.90 | $3.60 |
| Results tracked | 12 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
GLM-4.6V: 40.9 (#128), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1390 | 1465 |
| LMArena WebDev | — | 1400 |
Agentic & Tool Use Not comparable
GLM-4.6V: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
GLM-4.6V: 27.6 (#115), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1448 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |
Math Not comparable
GLM-4.6V: —, Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LMArena Math | — | 1454 |
Knowledge Qwen3.5 397B-A17B leads
GLM-4.6V: 38.0 (#149), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1371 | 1462 |
| GPQA Diamond | — | 86.4% |
Multimodal Qwen3.5 397B-A17B leads
GLM-4.6V: 34.8 (#90), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1164 | 1263 |
Multilingual Qwen3.5 397B-A17B leads
GLM-4.6V: 48.6 (#141), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1359 | 1430 |
| LMArena Chinese | 1425 | 1500 |
| LMArena Russian | 1340 | 1429 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Spanish | — | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
GLM-4.6V: 71.4 (#151), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1352 | 1424 |
Long Context Qwen3.5 397B-A17B leads
GLM-4.6V: 41.3 (#143), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1358 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
GLM-4.6V: 56.6 (#137), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | GLM-4.6V | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1377 | 1438 |
| LMArena Creative Writing | 1347 | 1401 |
| LMArena Multi-Turn | 1360 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is GLM-4.6V better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 41.3 on the Noometry Index. GLM-4.6V costs 3.0× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6V or Qwen3.5 397B-A17B?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is GLM-4.6V or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 128K.
How many benchmarks do GLM-4.6V and Qwen3.5 397B-A17B share?
12 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Qwen3.5 397B-A17B has 36.