Model comparison
GLM-4.5-Air vs GPT-4o
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 28.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and GPT-4o in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 33.8 to 10.2.
- The biggest single-benchmark swing is Omni-MATH: 39.1% for GLM-4.5-Air and 29.3% for GPT-4o.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- GLM-4.5-Air accepts more context: 131K tokens versus 128K.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | GPT-4o | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.7 | 28.5 |
| Released | 2025-07-20 | 2024-05-13 |
| Weights | Open | Proprietary |
| Context window | 131K | 128K |
| Max output | 98K | 16K |
| Input $ / M tokens | $0.20 | $2.50 |
| Output $ / M tokens | $1.10 | $10 |
| Results tracked | 27 | 72 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
GLM-4.5-Air: 34.5 (#225), GPT-4o: 25.1 (#323)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| GSO | 2.9% | 0% |
| LMArena Coding | 1397 | 1297 |
| SWE-bench Verified | — | 31% |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| WeirdML | — | 25.1% |
| BigCodeBench Instruct | — | 51.1% |
| LiveBench Coding | — | 51.4% |
| BigCodeBench Complete | — | 61.1% |
| CadEval | — | 26% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, GPT-4o: 20.8 (#133)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 23.3 (#166), GPT-4o: 9.4 (#338)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1281 |
| ForecastBench | 59.2 | 57.7 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 17.8% |
| Kagi LLM Benchmark | 43% | — |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| EnigmaEval | — | 0.8% |
| LiveBench Reasoning | — | 55.8% |
| DTBench | — | 64.5% |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 16.6% |
| Epoch Capabilities Index | — | 128.97 |
| LiveBench | — | 55.3% |
Math GLM-4.5-Air leads
GLM-4.5-Air: 33.8 (#166), GPT-4o: 10.2 (#303)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| Omni-MATH | 39.1% | 29.3% |
| LMArena Math | 1396 | 1285 |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| OTIS Mock AIME 2024-2025 | — | 6.4% |
| LiveBench Math | — | 49.5% |
| MATH Level 5 | — | 53.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 34.6 (#184), GPT-4o: 28.8 (#235)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| Humanity's Last Exam | 8.1% | 2.7% |
| MMLU-Pro | 76.2% | 71.3% |
| Vectara Hallucination Rate | 9.3% | 9.6% |
| GPQA (HELM) | 59.4% | 52% |
| LMArena Expert | 1370 | 1250 |
| GPQA Diamond | — | 49.2% |
| SimpleQA Verified | — | 26% |
| Confabulations | — | 15.3% |
| MMLU | — | 88.1% |
Multimodal Not comparable
GLM-4.5-Air: —, GPT-4o: 33.9 (#85)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| LMArena Vision | — | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.4 (#130), GPT-4o: 43.4 (#181)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| LMArena Non-English | 1366 | 1283 |
| LMArena Chinese | 1427 | 1277 |
| LMArena French | 1399 | 1303 |
| LMArena German | 1376 | 1282 |
| LMArena Japanese | 1348 | 1257 |
| LMArena Korean | 1306 | 1234 |
| LMArena Russian | 1373 | 1286 |
| LMArena Spanish | 1385 | 1292 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.8 (#165), GPT-4o: 66.8 (#202)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| IFEval | 81.2% | 81.7% |
| LMArena Instruction Following | 1353 | 1278 |
| LiveBench Instruction Following | — | 68.6% |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#130), GPT-4o: 39.4 (#174)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| LMArena Longer Query | 1367 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 56.1 (#134), GPT-4o: 52.8 (#160)
| Benchmark | GLM-4.5-Air | GPT-4o |
|---|---|---|
| LMArena Text | 1384 | 1300 |
| LMArena Creative Writing | 1343 | 1291 |
| WildBench | 78.9% | 82.8% |
| LMArena Multi-Turn | 1371 | 1302 |
| Short-Story Creative Writing | — | 81.8% |
| LiveBench Language | — | 47.6% |
Frequently asked questions
Is GLM-4.5-Air better than GPT-4o?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 28.5 on the Noometry Index.
Which is cheaper, GLM-4.5-Air or GPT-4o?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GPT-4o lists at $2.50 and $10.
Is GLM-4.5-Air or GPT-4o better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 34.5 versus 25.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.5-Air does, with 131K tokens against 128K.
How many benchmarks do GLM-4.5-Air and GPT-4o share?
26 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GPT-4o has 72.