Model comparison
GLM-4.5-Air vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 38.9 on the Noometry Index. GLM-4.5-Air costs 2.9× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. GLM-4.5-Air scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 35.0.
- The biggest single-benchmark swing is Omni-MATH: 39.1% for GLM-4.5-Air and 71.8% for Qwen3 235B-A22B.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
Side by side
| GLM-4.5-Air | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 38.9 | 43.5 |
| Released | 2025-07-20 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 98K | 16K |
| Input $ / M tokens | $0.20 | $0.70 |
| Output $ / M tokens | $1.10 | $2.80 |
| Results tracked | 27 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
GLM-4.5-Air: 33.3 (#259), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1397 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| GSO | 2.9% | — |
| WeirdML | — | 41% |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 43% | 69.4% |
| LMArena Hard Prompts | 1379 | 1433 |
| ForecastBench | 59.2 | 59.7 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.85 |
Math Qwen3 235B-A22B leads
GLM-4.5-Air: 36.2 (#170), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| Omni-MATH | 39.1% | 71.8% |
| LMArena Math | 1396 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
GLM-4.5-Air: 35.0 (#191), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| MMLU-Pro | 76.2% | 84.4% |
| Vectara Hallucination Rate | 9.3% | 9.3% |
| GPQA (HELM) | 59.4% | 72.7% |
| LMArena Expert | 1370 | 1463 |
| GPQA Diamond | — | 80.1% |
| Humanity's Last Exam | 8.1% | — |
| SimpleQA Verified | — | 40.4% |
| Confabulations | — | 15.6% |
Multilingual Qwen3 235B-A22B leads
GLM-4.5-Air: 49.1 (#135), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1366 | 1409 |
| LMArena Chinese | 1426 | 1481 |
| LMArena French | 1399 | 1445 |
| LMArena German | 1377 | 1433 |
| LMArena Japanese | 1348 | 1399 |
| LMArena Korean | 1308 | 1391 |
| LMArena Russian | 1373 | 1411 |
| LMArena Spanish | 1386 | 1430 |
Instruction Following Qwen3 235B-A22B leads
GLM-4.5-Air: 69.6 (#171), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 81.2% | 83.5% |
| LMArena Instruction Following | 1354 | 1408 |
Long Context Qwen3 235B-A22B leads
GLM-4.5-Air: 41.6 (#135), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1366 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
GLM-4.5-Air: 55.9 (#139), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | GLM-4.5-Air | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1384 | 1419 |
| LMArena Creative Writing | 1343 | 1384 |
| WildBench | 78.9% | 86.6% |
| LMArena Multi-Turn | 1371 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
Frequently asked questions
Is GLM-4.5-Air better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 38.9 on the Noometry Index. GLM-4.5-Air costs 2.9× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5-Air or Qwen3 235B-A22B?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is GLM-4.5-Air or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do GLM-4.5-Air and Qwen3 235B-A22B share?
25 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Qwen3 235B-A22B has 49.