Model comparison
GLM-4.7 vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 41.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. GLM-4.7 scores higher in 1 category and Qwen3.5 397B-A17B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 397B-A17B leads 33.6 to 23.7.
- The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 13% for Qwen3.5 397B-A17B.
- GLM-4.7 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 205K.
Side by side
| GLM-4.7 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.7 | 45.7 |
| Released | 2025-12-22 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.60 | $0.60 |
| Output $ / M tokens | $2.20 | $3.60 |
| Results tracked | 36 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 43.6 (#74), Qwen3.5 397B-A17B: 41.7 (#108)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1435 | 1400 |
| LMArena Coding | 1454 | 1464 |
| SciCode | 45.1% | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
GLM-4.7: 26.4 (#96), Qwen3.5 397B-A17B: 33.2 (#51)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| Vending-Bench 2 | 2,377 | — |
Reasoning Qwen3.5 397B-A17B leads
GLM-4.7: 23.7 (#161), Qwen3.5 397B-A17B: 33.6 (#62)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| Chess Puzzles | 6% | 13% |
| LMArena Hard Prompts | 1443 | 1448 |
| Epoch Capabilities Index | 143.53 | 146.64 |
| SimpleBench | 47.7% | — |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| CritPt | 1.7% | — |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
Math Qwen3.5 397B-A17B leads
GLM-4.7: 37.7 (#92), Qwen3.5 397B-A17B: 44.9 (#64)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 88.9% |
| LMArena Math | 1423 | 1455 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.5 397B-A17B leads
GLM-4.7: 47.0 (#74), Qwen3.5 397B-A17B: 53.3 (#53)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 83.3% | 86.4% |
| LMArena Expert | 1424 | 1461 |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
Multimodal Not comparable
GLM-4.7: —, Qwen3.5 397B-A17B: 40.0 (#42)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1262 |
Multilingual Too close to call
GLM-4.7: 53.0 (#75), Qwen3.5 397B-A17B: 54.0 (#56)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1417 | 1431 |
| LMArena Chinese | 1495 | 1501 |
| LMArena French | 1432 | 1461 |
| LMArena German | 1426 | 1447 |
| LMArena Japanese | 1439 | 1427 |
| LMArena Korean | 1401 | 1382 |
| LMArena Russian | 1423 | 1429 |
| LMArena Spanish | 1433 | 1443 |
Instruction Following Too close to call
GLM-4.7: 74.6 (#90), Qwen3.5 397B-A17B: 75.2 (#73)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1424 |
Long Context Qwen3.5 397B-A17B leads
GLM-4.7: 42.8 (#111), Qwen3.5 397B-A17B: 44.1 (#71)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1432 | 1442 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference Qwen3.5 397B-A17B leads
GLM-4.7: 61.1 (#89), Qwen3.5 397B-A17B: 62.5 (#74)
| Benchmark | GLM-4.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1436 | 1438 |
| LMArena Creative Writing | 1401 | 1401 |
| EQ-Bench Creative Writing | 1413 | 1478 |
| LMArena Multi-Turn | 1446 | 1447 |
Frequently asked questions
Is GLM-4.7 better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 41.7 on the Noometry Index.
Which is cheaper, GLM-4.7 or Qwen3.5 397B-A17B?
GLM-4.7 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-4.7 or Qwen3.5 397B-A17B better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 41.7 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 205K.
How many benchmarks do GLM-4.7 and Qwen3.5 397B-A17B share?
23 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen3.5 397B-A17B has 36.