Model comparison
GLM-4.5-Air vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 38.9 on the Noometry Index. GLM-4.5-Air costs 3.6× less per token, which makes it the better buy when GLM-5'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 GLM-5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 35.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 75% for GLM-5.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 131K.
Side by side
| GLM-4.5-Air | GLM-5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 38.9 | 46.1 |
| Released | 2025-07-20 | 2026-02-11 |
| Weights | Open | Open |
| Context window | 131K | 205K |
| Max output | 98K | 131K |
| Input $ / M tokens | $0.20 | $1 |
| Output $ / M tokens | $1.10 | $3.20 |
| Results tracked | 27 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-4.5-Air: 33.3 (#259), GLM-5: 49.0 (#52)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| LMArena Coding | 1397 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| GSO | 2.9% | — |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 765.62 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, GLM-5: 31.1 (#71)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
GLM-4.5-Air: 24.1 (#166), GLM-5: 27.6 (#116)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| Kagi LLM Benchmark | 43% | 75% |
| LMArena Hard Prompts | 1379 | 1452 |
| ForecastBench | 59.2 | 61 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| Chess Puzzles | — | 10% |
| Epoch Capabilities Index | — | 145.83 |
Math GLM-5 leads
GLM-4.5-Air: 36.2 (#170), GLM-5: 46.4 (#71)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| LMArena Math | 1396 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| OTIS Mock AIME 2024-2025 | — | 80% |
| Omni-MATH | 39.1% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
GLM-4.5-Air: 35.0 (#191), GLM-5: 52.3 (#64)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 10.1% |
| LMArena Expert | 1370 | 1454 |
| GPQA Diamond | — | 87.8% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual GLM-5 leads
GLM-4.5-Air: 49.1 (#135), GLM-5: 53.7 (#58)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| LMArena Non-English | 1366 | 1430 |
| LMArena Chinese | 1426 | 1511 |
| LMArena French | 1399 | 1455 |
| LMArena German | 1377 | 1445 |
| LMArena Japanese | 1348 | 1416 |
| LMArena Korean | 1308 | 1423 |
| LMArena Russian | 1373 | 1436 |
| LMArena Spanish | 1386 | 1454 |
Instruction Following GLM-5 leads
GLM-4.5-Air: 69.6 (#171), GLM-5: 75.2 (#67)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1354 | 1428 |
| IFEval | 81.2% | — |
Long Context GLM-5 leads
GLM-4.5-Air: 41.6 (#135), GLM-5: 44.7 (#60)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1366 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
GLM-4.5-Air: 55.9 (#139), GLM-5: 66.0 (#38)
| Benchmark | GLM-4.5-Air | GLM-5 |
|---|---|---|
| LMArena Text | 1384 | 1446 |
| LMArena Creative Writing | 1343 | 1439 |
| LMArena Multi-Turn | 1371 | 1456 |
| EQ-Bench Creative Writing | — | 1601 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 38.9 on the Noometry Index. GLM-4.5-Air costs 3.6× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5-Air or GLM-5?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-4.5-Air or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 131K.
How many benchmarks do GLM-4.5-Air and GLM-5 share?
20 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GLM-5 has 45.