Model comparison
GLM-4.5 vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 41.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GLM-4.5 scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.9% for GLM-4.5 and 73.7% for Qwen3.5 397B-A17B.
- GLM-4.5 is cheaper at $0.60 / $2.20 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 131K.
Side by side
| GLM-4.5 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 45.7 |
| Released | 2025-07-27 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 98K | 66K |
| Input $ / M tokens | $0.60 | $0.60 |
| Output $ / M tokens | $2.20 | $3.60 |
| Results tracked | 27 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5: 41.1 (#121), Qwen3.5 397B-A17B: 41.7 (#108)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1434 | 1464 |
| SWE-bench Verified (bash only) | 54.2% | — |
| LMArena WebDev | — | 1400 |
| WeirdML | 40.6% | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Qwen3.5 397B-A17B: 33.2 (#51)
| Benchmark | GLM-4.5 | 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-4.5: 27.7 (#99), Qwen3.5 397B-A17B: 33.6 (#62)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 73.7% |
| LMArena Hard Prompts | 1430 | 1448 |
| 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 | — | 146.64 |
Math Qwen3.5 397B-A17B leads
GLM-4.5: 36.3 (#119), Qwen3.5 397B-A17B: 44.9 (#64)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1427 | 1455 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
Knowledge Qwen3.5 397B-A17B leads
GLM-4.5: 35.5 (#172), Qwen3.5 397B-A17B: 53.3 (#53)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1433 | 1461 |
| GPQA Diamond | — | 86.4% |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
Multimodal Not comparable
GLM-4.5: —, Qwen3.5 397B-A17B: 40.0 (#42)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1262 |
Multilingual Too close to call
GLM-4.5: 53.0 (#74), Qwen3.5 397B-A17B: 54.0 (#56)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1417 | 1431 |
| LMArena Chinese | 1465 | 1501 |
| LMArena French | 1423 | 1461 |
| LMArena German | 1406 | 1447 |
| LMArena Japanese | 1416 | 1427 |
| LMArena Korean | 1382 | 1382 |
| LMArena Russian | 1414 | 1429 |
| LMArena Spanish | 1454 | 1443 |
Instruction Following Too close to call
GLM-4.5: 74.3 (#100), Qwen3.5 397B-A17B: 75.2 (#73)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1424 |
Long Context Qwen3.5 397B-A17B leads
GLM-4.5: 38.2 (#196), Qwen3.5 397B-A17B: 44.1 (#71)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1413 | 1442 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Qwen3.5 397B-A17B leads
GLM-4.5: 57.7 (#121), Qwen3.5 397B-A17B: 62.5 (#74)
| Benchmark | GLM-4.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1430 | 1438 |
| LMArena Creative Writing | 1395 | 1401 |
| EQ-Bench Creative Writing | 1343 | 1478 |
| LMArena Multi-Turn | 1415 | 1447 |
| Short-Story Creative Writing | 73.4% | — |
Frequently asked questions
Is GLM-4.5 better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 41.4 on the Noometry Index.
Which is cheaper, GLM-4.5 or Qwen3.5 397B-A17B?
GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is GLM-4.5 or Qwen3.5 397B-A17B better for coding?
They score almost the same on coding (41.1 vs 41.7); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 131K.
How many benchmarks do GLM-4.5 and Qwen3.5 397B-A17B share?
19 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Qwen3.5 397B-A17B has 36.