Model comparison
GLM-5.3 vs Qwen3.5 397B-A17B
GLM-5.3 is the stronger model overall, scoring 54.6 to 45.7 on the Noometry Index. Qwen3.5 397B-A17B costs 1.6× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. GLM-5.3 scores higher in 9 categories and Qwen3.5 397B-A17B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5.3 leads 59.0 to 41.7.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 68.8% for GLM-5.3 and 31.2% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.3.
- GLM-5.3 accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.3 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 54.6 | 45.7 |
| Released | 2026-08-14 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.40 | $0.60 |
| Output $ / M tokens | $4.40 | $3.60 |
| Results tracked | 41 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
GLM-5.3: 59.0 (#12), Qwen3.5 397B-A17B: 41.7 (#108)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1623 | 1400 |
| LMArena Coding | 1499 | 1464 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| ALE-Bench | 1,317 | — |
Agentic & Tool Use GLM-5.3 leads
GLM-5.3: 36.3 (#34), Qwen3.5 397B-A17B: 33.2 (#51)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | 56.6% | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| Vending-Bench 2 | 8,164 | — |
Reasoning GLM-5.3 leads
GLM-5.3: 45.2 (#42), Qwen3.5 397B-A17B: 33.6 (#62)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| NYT Connections (extended) | 74.2% | 58.9% |
| Chess Puzzles | 21% | 13% |
| LMArena Hard Prompts | 1491 | 1448 |
| Mystery Game Puzzles | 33% | 18% |
| DTBench | 87.7% | 87.5% |
| LMCA | 55.5% | 37.9% |
| Epoch Capabilities Index | 155.56 | 146.64 |
| Kagi LLM Benchmark | — | 73.7% |
| CritPt | 19.1% | — |
| Thematic Generalization | — | 65.1% |
| Bench to the Future 3 | 0.15 | — |
Math GLM-5.3 leads
GLM-5.3: 62.1 (#27), Qwen3.5 397B-A17B: 44.9 (#64)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.8% | 31.2% |
| OTIS Mock AIME 2024-2025 | 91.1% | 88.9% |
| LMArena Math | 1493 | 1455 |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 49% | — |
Knowledge GLM-5.3 leads
GLM-5.3: 58.3 (#34), Qwen3.5 397B-A17B: 53.3 (#53)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 90.9% | 86.4% |
| LMArena Expert | 1512 | 1461 |
| SimpleQA Verified | 41% | — |
Multimodal Not comparable
GLM-5.3: —, Qwen3.5 397B-A17B: 40.0 (#42)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1262 |
Multilingual GLM-5.3 leads
GLM-5.3: 55.9 (#27), Qwen3.5 397B-A17B: 54.0 (#56)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1457 | 1431 |
| LMArena Chinese | 1523 | 1501 |
| LMArena French | 1499 | 1461 |
| LMArena German | 1505 | 1447 |
| LMArena Japanese | 1438 | 1427 |
| LMArena Korean | 1478 | 1382 |
| LMArena Russian | 1460 | 1429 |
| LMArena Spanish | 1444 | 1443 |
Instruction Following GLM-5.3 leads
GLM-5.3: 77.8 (#15), Qwen3.5 397B-A17B: 75.2 (#73)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1481 | 1424 |
Long Context GLM-5.3 leads
GLM-5.3: 45.5 (#32), Qwen3.5 397B-A17B: 44.1 (#71)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1485 | 1442 |
Writing & Preference GLM-5.3 leads
GLM-5.3: 75.9 (#6), Qwen3.5 397B-A17B: 62.5 (#74)
| Benchmark | GLM-5.3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1473 | 1438 |
| LMArena Creative Writing | 1459 | 1401 |
| EQ-Bench Creative Writing | 2075 | 1478 |
| LMArena Multi-Turn | 1473 | 1447 |
Frequently asked questions
Is GLM-5.3 better than Qwen3.5 397B-A17B?
GLM-5.3 is the stronger model overall, scoring 54.6 to 45.7 on the Noometry Index. Qwen3.5 397B-A17B costs 1.6× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.
Which is cheaper, GLM-5.3 or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; GLM-5.3 lists at $1.40 and $4.40.
Is GLM-5.3 or Qwen3.5 397B-A17B better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.0 versus 41.7 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.3 and Qwen3.5 397B-A17B share?
29 benchmarks have published results for both models. GLM-5.3 has 41 scored results on Noometry and Qwen3.5 397B-A17B has 36.