Model comparison
GLM-5.3 vs Qwen3-30B-A3B
GLM-5.3 is the stronger model overall, scoring 54.8 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 10× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. GLM-5.3 scores higher in 9 categories and Qwen3-30B-A3B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.3 leads 62.3 to 37.4.
- The biggest single-benchmark swing is WeirdML: 75.4% for GLM-5.3 and 29.8% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $1.40 / $4.40 for GLM-5.3.
- GLM-5.3 accepts more context: 1M tokens versus 41K.
Side by side
| GLM-5.3 | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 54.8 | 38.9 |
| Released | 2026-08-14 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 1M | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $0.12 |
| Output $ / M tokens | $4.40 | $0.50 |
| Results tracked | 42 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
GLM-5.3: 59.5 (#14), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 59% | 33.3% |
| WeirdML | 75.4% | 29.8% |
| LMArena Coding | 1496 | 1416 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| CursorBench | 42.6% | — |
| LMArena WebDev | 1622 | — |
| FrontierSWE | 30.2% | — |
| ALE-Bench | 1,317 | — |
Agentic & Tool Use GLM-5.3 leads
GLM-5.3: 36.4 (#38), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Berkeley Function Calling Leaderboard | — | 41.4% |
| Vending-Bench 2 | 8,164 | — |
Reasoning GLM-5.3 leads
GLM-5.3: 46.1 (#46), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 19.1% | 0.3% |
| Chess Puzzles | 21% | 8% |
| LMArena Hard Prompts | 1489 | 1398 |
| DTBench | 87.7% | 69.3% |
| LMCA | 55.5% | 22.4% |
| Epoch Capabilities Index | 155.61 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| NYT Connections (extended) | 74.2% | — |
| Mystery Game Puzzles | 33% | — |
| Bench to the Future 3 | 0.15 | — |
Math GLM-5.3 leads
GLM-5.3: 62.3 (#33), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.1% | 70.3% |
| LMArena Math | 1489 | 1394 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | — | 47.8% |
| ProofBench | 49% | — |
Knowledge GLM-5.3 leads
GLM-5.3: 58.3 (#37), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 90.9% | 70.1% |
| LMArena Expert | 1516 | 1396 |
| SimpleQA Verified | 41% | — |
| Confabulations | — | 12.3% |
Multilingual GLM-5.3 leads
GLM-5.3: 55.7 (#28), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1457 | 1372 |
| LMArena Chinese | 1528 | 1433 |
| LMArena French | 1499 | 1418 |
| LMArena German | 1499 | 1380 |
| LMArena Japanese | 1453 | 1337 |
| LMArena Korean | 1472 | 1331 |
| LMArena Russian | 1463 | 1370 |
| LMArena Spanish | 1460 | 1404 |
Instruction Following GLM-5.3 leads
GLM-5.3: 77.5 (#23), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1363 |
Long Context GLM-5.3 leads
GLM-5.3: 45.4 (#41), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1482 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference GLM-5.3 leads
GLM-5.3: 75.7 (#6), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | GLM-5.3 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1471 | 1384 |
| LMArena Creative Writing | 1457 | 1317 |
| LMArena Multi-Turn | 1472 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 2075 | — |
Frequently asked questions
Is GLM-5.3 better than Qwen3-30B-A3B?
GLM-5.3 is the stronger model overall, scoring 54.8 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 10× 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 Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; GLM-5.3 lists at $1.40 and $4.40.
Is GLM-5.3 or Qwen3-30B-A3B better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.5 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3 does, with 1M tokens against 41K.
How many benchmarks do GLM-5.3 and Qwen3-30B-A3B share?
26 benchmarks have published results for both models. GLM-5.3 has 42 scored results on Noometry and Qwen3-30B-A3B has 32.