Model comparison
GLM-5.3-Flash vs Qwen3.5-9B
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 33.8 on the Noometry Index. Qwen3.5-9B costs 2.1× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. GLM-5.3-Flash scores higher in 5 categories and Qwen3.5-9B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 23.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 61.7% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.15 / $0.50 for GLM-5.3-Flash.
- GLM-5.3-Flash accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.3-Flash | Qwen3.5-9B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 51.8 | 33.8 |
| Released | 2026-08-20 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.15 | $0.10 |
| Output $ / M tokens | $0.50 | $0.15 |
| Results tracked | 40 | 10 |
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: 53.1 (#31), Qwen3.5-9B: 35.9 (#217)
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| SciCode | 51.6% | 27.5% |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| LMArena Coding | 1508 | — |
| ALE-Bench | 303.55 | — |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), Qwen3.5-9B: 14.5 (#151)
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), Qwen3.5-9B: 23.1 (#182)
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| CritPt | 15.4% | 0.3% |
| Chess Puzzles | 14% | 12% |
| Epoch Capabilities Index | 151.88 | 139.46 |
| ARC-AGI-2 | 65.8% | — |
| ARC-AGI-1 | 91% | — |
| LMArena Hard Prompts | 1491 | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), Qwen3.5-9B: 34.8 (#192)
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 61.7% |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | — | 48.5% |
| ProofBench | 21% | — |
| LMArena Math | 1500 | — |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), Qwen3.5-9B: 46.0 (#84)
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 90.2% | 79% |
| LMArena Expert | 1513 | — |
Multimodal Not comparable
GLM-5.3-Flash: 42.8 (#27), Qwen3.5-9B: —
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| LMArena Vision | 1296 | — |
Multilingual Not comparable
GLM-5.3-Flash: 56.0 (#25), Qwen3.5-9B: —
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1462 | — |
| LMArena Chinese | 1527 | — |
| LMArena French | 1496 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1446 | — |
| LMArena Russian | 1469 | — |
| LMArena Spanish | 1471 | — |
Instruction Following Not comparable
GLM-5.3-Flash: 77.5 (#20), Qwen3.5-9B: —
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1478 | — |
Long Context Not comparable
GLM-5.3-Flash: 45.4 (#39), Qwen3.5-9B: —
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1482 | — |
Writing & Preference Not comparable
GLM-5.3-Flash: 65.3 (#50), Qwen3.5-9B: —
| Benchmark | GLM-5.3-Flash | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1471 | — |
| LMArena Creative Writing | 1442 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is GLM-5.3-Flash better than Qwen3.5-9B?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 33.8 on the Noometry Index. Qwen3.5-9B costs 2.1× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Which is cheaper, GLM-5.3-Flash or Qwen3.5-9B?
Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; GLM-5.3-Flash lists at $0.15 and $0.50.
Is GLM-5.3-Flash or Qwen3.5-9B better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 262K.
How many benchmarks do GLM-5.3-Flash and Qwen3.5-9B share?
6 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Qwen3.5-9B has 10.