Model comparison
GLM-4.6 vs Qwen3.5 35B-A3B
GLM-4.6 and Qwen3.5 35B-A3B score almost the same on the Noometry Index (40.9 vs 41.7), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. GLM-4.6 scores higher in 5 categories and Qwen3.5 35B-A3B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.7 to 39.6.
- The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 29.3% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Qwen3.5 35B-A3B accepts more context: 262K tokens versus 205K.
Side by side
| GLM-4.6 | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 40.9 | 41.7 |
| Released | 2025-09-30 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.60 | $0.25 |
| Output $ / M tokens | $2.20 | $2 |
| Results tracked | 29 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Qwen3.5 35B-A3B: 33.5 (#244)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena WebDev | 1339 | 1254 |
| SciCode | 38.4% | 29.3% |
| LMArena Coding | 1449 | 1410 |
| SWE-bench Verified (bash only) | 55.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.1 (#60), Qwen3.5 35B-A3B: —
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Too close to call
GLM-4.6: 23.1 (#168), Qwen3.5 35B-A3B: 23.9 (#158)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 1.1% | 0.6% |
| LMArena Hard Prompts | 1440 | 1400 |
| Kagi LLM Benchmark | 47.4% | — |
| Chess Puzzles | — | 10% |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |
Math Qwen3.5 35B-A3B leads
GLM-4.6: 36.4 (#115), Qwen3.5 35B-A3B: 38.4 (#86)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Math | 1431 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.5 35B-A3B leads
GLM-4.6: 39.6 (#118), Qwen3.5 35B-A3B: 47.7 (#73)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 10.5% |
| LMArena Expert | 1432 | 1408 |
| GPQA Diamond | — | 83.5% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Qwen3.5 35B-A3B: 50.2 (#122)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1426 | 1379 |
| LMArena Chinese | 1500 | 1458 |
| LMArena French | 1459 | 1412 |
| LMArena German | 1447 | 1367 |
| LMArena Japanese | 1394 | 1326 |
| LMArena Korean | 1401 | 1354 |
| LMArena Russian | 1418 | 1377 |
| LMArena Spanish | 1436 | 1390 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.5 (#93), Qwen3.5 35B-A3B: 73.0 (#123)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1410 | 1379 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#91), Qwen3.5 35B-A3B: 42.4 (#122)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1423 | 1390 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Qwen3.5 35B-A3B: 58.1 (#118)
| Benchmark | GLM-4.6 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1440 | 1395 |
| LMArena Creative Writing | 1411 | 1347 |
| LMArena Multi-Turn | 1427 | 1391 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Qwen3.5 35B-A3B?
GLM-4.6 and Qwen3.5 35B-A3B score almost the same on the Noometry Index (40.9 vs 41.7), so choose on price, context window or the category you care about most.
Which is cheaper, GLM-4.6 or Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Qwen3.5 35B-A3B better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 35B-A3B does, with 262K tokens against 205K.
How many benchmarks do GLM-4.6 and Qwen3.5 35B-A3B share?
21 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen3.5 35B-A3B has 28.