Model comparison
GLM-5.3-Flash vs Qwen3.5-Flash
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 42.3 on the Noometry Index.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. GLM-5.3-Flash scores higher in 7 categories and Qwen3.5-Flash in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5.3-Flash leads 53.7 to 33.9.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 55.8% for GLM-5.3-Flash and 18.2% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.15 / $0.50 for GLM-5.3-Flash.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-5.3-Flash | Qwen3.5-Flash | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 49.6 | 42.3 |
| Released | 2026-08-20 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.15 | $0.10 |
| Output $ / M tokens | $0.50 | $0.40 |
| Results tracked | 36 | 32 |
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), Qwen3.5-Flash: 33.9 (#234)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1614 | 1243 |
| LMArena Coding | 1506 | 1412 |
| ALE-Bench | 303.55 | 221.8 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| SciCode | 51.6% | — |
Agentic & Tool Use Not comparable
GLM-5.3-Flash: 34.3 (#41), Qwen3.5-Flash: —
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
GLM-5.3-Flash: 31.7 (#69), Qwen3.5-Flash: 32.9 (#63)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 14% | 21% |
| LMArena Hard Prompts | 1490 | 1404 |
| Mystery Game Puzzles | 8% | 20% |
| Epoch Capabilities Index | 151.9 | 143.98 |
| CritPt | 15.4% | — |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
| 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), Qwen3.5-Flash: 36.3 (#117)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 18.2% |
| OTIS Mock AIME 2024-2025 | 93.9% | 84.4% |
| LMArena Math | 1499 | 1407 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#33), Qwen3.5-Flash: 43.2 (#84)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 90.2% | 82.3% |
| LMArena Expert | 1512 | 1408 |
| SimpleQA Verified | — | 20.3% |
| Vectara Hallucination Rate | — | 10.5% |
Multimodal Not comparable
GLM-5.3-Flash: 42.6 (#25), Qwen3.5-Flash: —
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1304 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.2 (#24), Qwen3.5-Flash: 50.7 (#116)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1462 | 1385 |
| LMArena Chinese | 1529 | 1446 |
| LMArena French | 1495 | 1412 |
| LMArena German | 1457 | 1389 |
| LMArena Japanese | 1420 | 1369 |
| LMArena Korean | 1443 | 1344 |
| LMArena Russian | 1472 | 1379 |
| LMArena Spanish | 1471 | 1399 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.8 (#17), Qwen3.5-Flash: 72.8 (#133)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1480 | 1374 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.3 (#41), Qwen3.5-Flash: 42.4 (#119)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1479 | 1392 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.4 (#49), Qwen3.5-Flash: 58.2 (#117)
| Benchmark | GLM-5.3-Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1471 | 1397 |
| LMArena Creative Writing | 1440 | 1343 |
| LMArena Multi-Turn | 1471 | 1393 |
Frequently asked questions
Is GLM-5.3-Flash better than Qwen3.5-Flash?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 42.3 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GLM-5.3-Flash lists at $0.15 and $0.50.
Is GLM-5.3-Flash or Qwen3.5-Flash better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 33.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do GLM-5.3-Flash and Qwen3.5-Flash share?
25 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Qwen3.5-Flash has 32.