Model comparison
GLM-5.1 vs Qwen3 32B
GLM-5.1 is the stronger model overall, scoring 47.8 to 39.2 on the Noometry Index. Qwen3 32B costs 1.8× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Qwen3 32B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 20.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 66.9% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 131K.
Side by side
| GLM-5.1 | Qwen3 32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.8 | 39.2 |
| Released | 2026-04-07 | 2025-04 |
| Weights | Open | Open |
| Context window | 200K | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $0.70 |
| Output $ / M tokens | $4.40 | $2.80 |
| Results tracked | 41 | 26 |
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 32B: 37.7 (#190)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| SciCode | 43.8% | 35.4% |
| LMArena Coding | 1485 | 1358 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 40% |
| LMArena WebDev | 1508 | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Qwen3 32B leads
GLM-5.1: 24.9 (#113), Qwen3 32B: 32.6 (#62)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 48.7% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Qwen3 32B: 20.2 (#241)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| CritPt | 4.6% | 0.3% |
| Chess Puzzles | 19% | 5% |
| LMArena Hard Prompts | 1472 | 1334 |
| Epoch Capabilities Index | 149.84 | 138.51 |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 54.9% |
| NYT Connections (extended) | 77.7% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Qwen3 32B: 39.7 (#99)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 66.9% |
| LMArena Math | 1473 | 1399 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| 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 32B: 40.0 (#125)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 89.9% | 65.7% |
| LMArena Expert | 1476 | 1362 |
| SimpleQA Verified | 34% | — |
| Vectara Hallucination Rate | — | 5.9% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Qwen3 32B: 45.6 (#167)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1447 | 1317 |
| LMArena Chinese | 1515 | 1357 |
| LMArena German | 1465 | 1341 |
| LMArena Russian | 1454 | 1311 |
| LMArena French | 1474 | — |
| LMArena Japanese | 1434 | — |
| LMArena Korean | 1418 | — |
| LMArena Spanish | 1469 | — |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Qwen3 32B: 68.9 (#179)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1305 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Qwen3 32B: 43.8 (#87)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1466 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Qwen3 32B: 52.9 (#163)
| Benchmark | GLM-5.1 | Qwen3 32B |
|---|---|---|
| LMArena Text | 1461 | 1340 |
| LMArena Creative Writing | 1453 | 1297 |
| LMArena Multi-Turn | 1472 | 1331 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than Qwen3 32B?
GLM-5.1 is the stronger model overall, scoring 47.8 to 39.2 on the Noometry Index. Qwen3 32B costs 1.8× 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 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Qwen3 32B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 131K.
How many benchmarks do GLM-5.1 and Qwen3 32B share?
19 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3 32B has 26.