Model comparison
GLM-5.1 vs Qwen3.5 35B-A3B
GLM-5.1 is the stronger model overall, scoring 47.8 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 3.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Qwen3.5 35B-A3B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5.1 leads 48.7 to 33.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 70% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Qwen3.5 35B-A3B accepts more context: 262K tokens versus 200K.
Side by side
| GLM-5.1 | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.8 | 42.0 |
| Released | 2026-04-07 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 200K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.40 | $0.25 |
| Output $ / M tokens | $4.40 | $2 |
| Results tracked | 41 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena WebDev | 1508 | 1254 |
| SciCode | 43.8% | 29.3% |
| LMArena Coding | 1485 | 1410 |
| SWE-bench Verified | 74.2% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Not comparable
GLM-5.1: 24.9 (#113), Qwen3.5 35B-A3B: —
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 4.6% | 0.6% |
| Chess Puzzles | 19% | 10% |
| LMArena Hard Prompts | 1472 | 1400 |
| Epoch Capabilities Index | 149.84 | 142.52 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| MathArena Final-Answer Competitions | 67.1% | 56% |
| OTIS Mock AIME 2024-2025 | 93.3% | 70% |
| LMArena Math | 1473 | 1404 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 89.9% | 83.5% |
| LMArena Expert | 1476 | 1408 |
| SimpleQA Verified | 34% | — |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1447 | 1378 |
| LMArena Chinese | 1515 | 1457 |
| LMArena French | 1474 | 1412 |
| LMArena German | 1465 | 1367 |
| LMArena Japanese | 1434 | 1325 |
| LMArena Korean | 1418 | 1356 |
| LMArena Russian | 1454 | 1376 |
| LMArena Spanish | 1469 | 1392 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1379 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1466 | 1389 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | GLM-5.1 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1461 | 1395 |
| LMArena Creative Writing | 1453 | 1346 |
| LMArena Multi-Turn | 1472 | 1390 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than Qwen3.5 35B-A3B?
GLM-5.1 is the stronger model overall, scoring 47.8 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 3.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 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-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Qwen3.5 35B-A3B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 35B-A3B does, with 262K tokens against 200K.
How many benchmarks do GLM-5.1 and Qwen3.5 35B-A3B share?
25 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3.5 35B-A3B has 28.