Model comparison
GLM-5 vs QwQ-32B
GLM-5 is the stronger model overall, scoring 45.9 to 39.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. GLM-5 scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5 leads 66.2 to 50.9.
- The biggest single-benchmark swing is GPQA Diamond: 87.8% for GLM-5 and 65.3% for QwQ-32B.
Side by side
| GLM-5 | QwQ-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 45.9 | 39.4 |
| Released | 2026-02-11 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 45 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#47), QwQ-32B: 34.9 (#220)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1461 | 1333 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 30.9 (#65), QwQ-32B: —
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#100), QwQ-32B: 22.9 (#171)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 10% | 5% |
| LMArena Hard Prompts | 1451 | 1326 |
| Epoch Capabilities Index | 145.84 | 137.6 |
| ForecastBench | 61 | 58.3 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| LiveBench | — | 72% |
Math GLM-5 leads
GLM-5: 44.8 (#66), QwQ-32B: 36.2 (#123)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 59.2% |
| LMArena Math | 1440 | 1359 |
| MathArena Final-Answer Competitions | 65.7% | — |
| LiveBench Math | — | 77.8% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.2 (#59), QwQ-32B: 37.2 (#150)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 87.8% | 65.3% |
| LMArena Expert | 1454 | 1323 |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 10.1% | — |
Multilingual GLM-5 leads
GLM-5: 53.9 (#57), QwQ-32B: 45.0 (#171)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1430 | 1306 |
| LMArena Chinese | 1511 | 1378 |
| LMArena French | 1455 | 1337 |
| LMArena German | 1445 | 1313 |
| LMArena Japanese | 1416 | 1263 |
| LMArena Korean | 1421 | 1278 |
| LMArena Russian | 1436 | 1297 |
| LMArena Spanish | 1452 | 1353 |
Instruction Following GLM-5 leads
GLM-5: 75.4 (#64), QwQ-32B: 72.8 (#131)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1427 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
GLM-5: 44.6 (#58), QwQ-32B: 49.0 (#11)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1446 | 1308 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.2 (#38), QwQ-32B: 50.9 (#175)
| Benchmark | GLM-5 | QwQ-32B |
|---|---|---|
| LMArena Text | 1446 | 1329 |
| LMArena Creative Writing | 1438 | 1288 |
| EQ-Bench Creative Writing | 1601 | 1257 |
| LMArena Multi-Turn | 1456 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is GLM-5 better than QwQ-32B?
GLM-5 is the stronger model overall, scoring 45.9 to 39.4 on the Noometry Index.
Is GLM-5 or QwQ-32B better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 34.9 in the Noometry coding category.
How many benchmarks do GLM-5 and QwQ-32B share?
23 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and QwQ-32B has 36.