Model comparison
GLM-5.3-Flash vs Qwen3 32B
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 38.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GLM-5.3-Flash scores higher in 9 categories and Qwen3 32B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 40.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 66.9% for Qwen3 32B.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- GLM-5.3-Flash accepts more context: 1M tokens versus 131K.
Side by side
| GLM-5.3-Flash | Qwen3 32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 49.6 | 38.8 |
| Released | 2026-08-20 | 2025-04 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.15 | $0.70 |
| Output $ / M tokens | $0.50 | $2.80 |
| Results tracked | 36 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.7 (#26), Qwen3 32B: 37.3 (#184)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| SciCode | 51.6% | 35.4% |
| LMArena Coding | 1506 | 1358 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| Aider Polyglot | — | 40% |
| LMArena WebDev | 1614 | — |
| ALE-Bench | 303.55 | — |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.3 (#41), Qwen3 32B: 32.3 (#58)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| APEX-Agents | 52.8% | — |
| Berkeley Function Calling Leaderboard | — | 48.7% |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 31.7 (#69), Qwen3 32B: 19.6 (#233)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| CritPt | 15.4% | 0.3% |
| Chess Puzzles | 14% | 5% |
| LMArena Hard Prompts | 1490 | 1335 |
| Epoch Capabilities Index | 151.9 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#38), Qwen3 32B: 37.9 (#89)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 66.9% |
| LMArena Math | 1499 | 1399 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#33), Qwen3 32B: 40.0 (#112)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 90.2% | 65.7% |
| LMArena Expert | 1512 | 1362 |
| Vectara Hallucination Rate | — | 5.9% |
Multimodal Not comparable
GLM-5.3-Flash: 42.6 (#25), Qwen3 32B: —
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1304 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.2 (#24), Qwen3 32B: 45.8 (#162)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1462 | 1317 |
| LMArena Chinese | 1529 | 1357 |
| LMArena German | 1457 | 1341 |
| LMArena Russian | 1472 | 1311 |
| LMArena French | 1495 | — |
| LMArena Japanese | 1420 | — |
| LMArena Korean | 1443 | — |
| LMArena Spanish | 1471 | — |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.8 (#17), Qwen3 32B: 69.1 (#174)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1480 | 1305 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.3 (#41), Qwen3 32B: 43.7 (#83)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1479 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.4 (#49), Qwen3 32B: 53.1 (#158)
| Benchmark | GLM-5.3-Flash | Qwen3 32B |
|---|---|---|
| LMArena Text | 1471 | 1340 |
| LMArena Creative Writing | 1440 | 1297 |
| LMArena Multi-Turn | 1471 | 1331 |
Frequently asked questions
Is GLM-5.3-Flash better than Qwen3 32B?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 38.8 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Qwen3 32B?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.
Is GLM-5.3-Flash or Qwen3 32B better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 37.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 131K.
How many benchmarks do GLM-5.3-Flash and Qwen3 32B share?
19 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Qwen3 32B has 26.