Model comparison
GLM-4.5-Air vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 38.9 on the Noometry Index. GLM-4.5-Air costs 4.0× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and GPT-5.4 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 35.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 37.9% for GPT-5.4 mini.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 131K.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | GPT-5.4 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.9 | 45.0 |
| Released | 2025-07-20 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 131K | 400K |
| Max output | 98K | 128K |
| Input $ / M tokens | $0.20 | $0.75 |
| Output $ / M tokens | $1.10 | $4.50 |
| Results tracked | 27 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GLM-4.5-Air: 33.3 (#259), GPT-5.4 mini: 45.2 (#72)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1397 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| GSO | 2.9% | — |
| WeirdML | — | 60.3% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, GPT-5.4 mini: 29.9 (#81)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
GLM-4.5-Air: 24.1 (#166), GPT-5.4 mini: 30.4 (#85)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| Kagi LLM Benchmark | 43% | 37.9% |
| LMArena Hard Prompts | 1379 | 1424 |
| ForecastBench | 59.2 | 57 |
| ARC-AGI-2 | — | 18.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| DTBench | — | 80% |
| LMCA | — | 40.8% |
| Epoch Capabilities Index | — | 148.84 |
Math GPT-5.4 mini leads
GLM-4.5-Air: 36.2 (#170), GPT-5.4 mini: 45.5 (#75)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| LMArena Math | 1396 | 1419 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 21% |
| Omni-MATH | 39.1% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
GLM-4.5-Air: 35.0 (#191), GPT-5.4 mini: 51.5 (#67)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 5.5% |
| LMArena Expert | 1370 | 1435 |
| GPQA Diamond | — | 86.9% |
| Humanity's Last Exam | 8.1% | — |
| SimpleQA Verified | — | 29.4% |
| MMLU-Pro | 76.2% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
GLM-4.5-Air: —, GPT-5.4 mini: 39.7 (#56)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual GPT-5.4 mini leads
GLM-4.5-Air: 49.1 (#135), GPT-5.4 mini: 51.9 (#96)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1366 | 1405 |
| LMArena Chinese | 1426 | 1446 |
| LMArena French | 1399 | 1440 |
| LMArena German | 1377 | 1409 |
| LMArena Japanese | 1348 | 1374 |
| LMArena Korean | 1308 | 1368 |
| LMArena Russian | 1373 | 1417 |
| LMArena Spanish | 1386 | 1405 |
Instruction Following GPT-5.4 mini leads
GLM-4.5-Air: 69.6 (#171), GPT-5.4 mini: 74.1 (#102)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1354 | 1405 |
| IFEval | 81.2% | — |
Long Context GPT-5.4 mini leads
GLM-4.5-Air: 41.6 (#135), GPT-5.4 mini: 43.0 (#112)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1366 | 1407 |
Writing & Preference GPT-5.4 mini leads
GLM-4.5-Air: 55.9 (#139), GPT-5.4 mini: 64.0 (#58)
| Benchmark | GLM-4.5-Air | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1384 | 1412 |
| LMArena Creative Writing | 1343 | 1370 |
| LMArena Multi-Turn | 1371 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 38.9 on the Noometry Index. GLM-4.5-Air costs 4.0× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5-Air or GPT-5.4 mini?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GLM-4.5-Air or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 131K.
How many benchmarks do GLM-4.5-Air and GPT-5.4 mini share?
20 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GPT-5.4 mini has 46.