Model comparison
GLM-5.1 vs Qwen1.5-32B
GLM-5.1 is the stronger model overall, scoring 47.6 to 30.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 55.0 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 89.9% for GLM-5.1 and 30.7% for Qwen1.5-32B.
Side by side
| GLM-5.1 | Qwen1.5-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.6 | 30.0 |
| Released | 2026-04-07 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 41 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.5 (#52), Qwen1.5-32B: 31.1 (#278)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1486 | 1155 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Not comparable
GLM-5.1: 24.8 (#106), Qwen1.5-32B: —
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 38.2 (#57), Qwen1.5-32B: 20.9 (#210)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1131 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| Epoch Capabilities Index | 149.86 | — |
Math GLM-5.1 leads
GLM-5.1: 49.0 (#48), Qwen1.5-32B: 30.5 (#207)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1472 | 1155 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 55.0 (#45), Qwen1.5-32B: 13.5 (#291)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 89.9% | 30.7% |
| LMArena Expert | 1477 | 1126 |
| SimpleQA Verified | 34% | — |
| MMLU | — | 74.4% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.2 (#34), Qwen1.5-32B: 31.6 (#254)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1448 | 1106 |
| LMArena Chinese | 1516 | 1176 |
| LMArena French | 1478 | 1100 |
| LMArena German | 1466 | 1058 |
| LMArena Japanese | 1436 | 1027 |
| LMArena Korean | 1423 | 1007 |
| LMArena Russian | 1453 | 1073 |
| LMArena Spanish | 1467 | 1089 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.5 (#41), Qwen1.5-32B: 58.0 (#260)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1116 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#51), Qwen1.5-32B: 34.7 (#241)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1467 | 1146 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 67.2 (#29), Qwen1.5-32B: 34.4 (#266)
| Benchmark | GLM-5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1462 | 1137 |
| LMArena Creative Writing | 1454 | 1083 |
| LMArena Multi-Turn | 1473 | 1140 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than Qwen1.5-32B?
GLM-5.1 is the stronger model overall, scoring 47.6 to 30.0 on the Noometry Index.
Is GLM-5.1 or Qwen1.5-32B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.5 versus 31.1 in the Noometry coding category.
How many benchmarks do GLM-5.1 and Qwen1.5-32B share?
18 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen1.5-32B has 21.