Model comparison
GLM-4.5-Air vs GPT-5.5 Pro
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 38.9 on the Noometry Index. GLM-4.5-Air costs 159× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in reasoning, where GPT-5.5 Pro leads 73.3 to 24.1.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $30 / $180 for GPT-5.5 Pro.
- GPT-5.5 Pro accepts more context: 1.05M tokens versus 131K.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | GPT-5.5 Pro | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.9 | 64.3 |
| Released | 2025-07-20 | 2026-04-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 98K | 128K |
| Input $ / M tokens | $0.20 | $30 |
| Output $ / M tokens | $1.10 | $180 |
| Results tracked | 27 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GLM-4.5-Air: 33.3 (#259), GPT-5.5 Pro: —
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| GSO | 2.9% | — |
| LMArena Coding | 1397 | — |
Reasoning GPT-5.5 Pro leads
GLM-4.5-Air: 24.1 (#166), GPT-5.5 Pro: 73.3 (#10)
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| ARC-AGI-2 | — | 84.6% |
| SimpleBench | — | 76.9% |
| Kagi LLM Benchmark | 43% | — |
| ARC-AGI-1 | — | 96.5% |
| CritPt | — | 30.6% |
| Chess Puzzles | — | 64% |
| LMArena Hard Prompts | 1379 | — |
| DTBench | — | 96% |
| LMCA | — | 53.9% |
| Epoch Capabilities Index | — | 162.07 |
| ForecastBench | 59.2 | — |
Math GPT-5.5 Pro leads
GLM-4.5-Air: 36.2 (#170), GPT-5.5 Pro: 84.0 (#10)
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 87.7% |
| FrontierMath Tier 4 | — | 78% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| Omni-MATH | 39.1% | — |
| LMArena Math | 1396 | — |
| FrontierMath (Feb 2025 set) | — | 52.4% |
| FrontierMath Tier 4 (v1) | — | 39.6% |
Knowledge GPT-5.5 Pro leads
GLM-4.5-Air: 35.0 (#191), GPT-5.5 Pro: 64.1 (#19)
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| GPQA Diamond | — | 93.9% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1370 | — |
Multilingual Not comparable
GLM-4.5-Air: 49.1 (#135), GPT-5.5 Pro: —
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| LMArena Non-English | 1366 | — |
| LMArena Chinese | 1426 | — |
| LMArena French | 1399 | — |
| LMArena German | 1377 | — |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1308 | — |
| LMArena Russian | 1373 | — |
| LMArena Spanish | 1386 | — |
Instruction Following Not comparable
GLM-4.5-Air: 69.6 (#171), GPT-5.5 Pro: —
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| IFEval | 81.2% | — |
| LMArena Instruction Following | 1354 | — |
Long Context Not comparable
GLM-4.5-Air: 41.6 (#135), GPT-5.5 Pro: —
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| LMArena Longer Query | 1366 | — |
Writing & Preference Not comparable
GLM-4.5-Air: 55.9 (#139), GPT-5.5 Pro: —
| Benchmark | GLM-4.5-Air | GPT-5.5 Pro |
|---|---|---|
| LMArena Text | 1384 | — |
| LMArena Creative Writing | 1343 | — |
| WildBench | 78.9% | — |
| LMArena Multi-Turn | 1371 | — |
Frequently asked questions
Is GLM-4.5-Air better than GPT-5.5 Pro?
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 38.9 on the Noometry Index. GLM-4.5-Air costs 159× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5-Air or GPT-5.5 Pro?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GPT-5.5 Pro lists at $30 and $180.
Which has the bigger context window?
GPT-5.5 Pro does, with 1.05M tokens against 131K.
How many benchmarks do GLM-4.5-Air and GPT-5.5 Pro share?
0 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GPT-5.5 Pro has 14.