Model comparison
GLM-4.5-Air vs GPT-6 Luna
GPT-6 Luna is the stronger model overall, scoring 53.3 to 38.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and GPT-6 Luna in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 36.2.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
- GPT-6 Luna 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-6 Luna | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.9 | 53.3 |
| Released | 2025-07-20 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 98K | 128K |
| Input $ / M tokens | $0.20 | $0.10 |
| Output $ / M tokens | $1.10 | $0.50 |
| Results tracked | 27 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GLM-4.5-Air: 33.3 (#259), GPT-6 Luna: 55.5 (#25)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Coding | 1397 | 1439 |
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| LMArena WebDev | — | 1581 |
| SciCode | — | 54.6% |
| GSO | 2.9% | — |
| ALE-Bench | — | 1,577 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, GPT-6 Luna: 33.3 (#54)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| APEX-Agents | — | 44.3% |
| GDP.pdf | — | 23% |
Reasoning GPT-6 Luna leads
GLM-4.5-Air: 24.1 (#166), GPT-6 Luna: 48.2 (#41)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1411 |
| ARC-AGI-2 | — | 59.3% |
| Kagi LLM Benchmark | 43% | — |
| NYT Connections (extended) | — | 68.7% |
| ARC-AGI-1 | — | 86.7% |
| CritPt | — | 19.4% |
| Chess Puzzles | — | 31% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 90.1% |
| LMCA | — | 44.5% |
| Epoch Capabilities Index | — | 156.28 |
| ForecastBench | 59.2 | — |
Math GPT-6 Luna leads
GLM-4.5-Air: 36.2 (#170), GPT-6 Luna: 76.1 (#15)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Math | 1396 | 1416 |
| FrontierMath (Tiers 1-3) | — | 78.9% |
| FrontierMath Tier 4 | — | 56.1% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 64% |
| Omni-MATH | 39.1% | — |
Knowledge GPT-6 Luna leads
GLM-4.5-Air: 35.0 (#191), GPT-6 Luna: 57.0 (#41)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Expert | 1370 | 1444 |
| GPQA Diamond | — | 90.5% |
| Humanity's Last Exam | 8.1% | — |
| SimpleQA Verified | — | 41.4% |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
GLM-4.5-Air: —, GPT-6 Luna: 42.4 (#30)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Vision | — | 1217 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 44.2% |
Multilingual GPT-6 Luna leads
GLM-4.5-Air: 49.1 (#135), GPT-6 Luna: 50.5 (#117)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1366 | 1386 |
| LMArena Chinese | 1426 | 1433 |
| LMArena French | 1399 | 1420 |
| LMArena German | 1377 | 1369 |
| LMArena Japanese | 1348 | 1369 |
| LMArena Korean | 1308 | 1360 |
| LMArena Russian | 1373 | 1394 |
| LMArena Spanish | 1386 | 1393 |
Instruction Following GPT-6 Luna leads
GLM-4.5-Air: 69.6 (#171), GPT-6 Luna: 74.3 (#99)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1354 | 1409 |
| IFEval | 81.2% | — |
Long Context GPT-6 Luna leads
GLM-4.5-Air: 41.6 (#135), GPT-6 Luna: 43.0 (#111)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1366 | 1409 |
Writing & Preference GPT-6 Luna leads
GLM-4.5-Air: 55.9 (#139), GPT-6 Luna: 58.3 (#119)
| Benchmark | GLM-4.5-Air | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1384 | 1391 |
| LMArena Creative Writing | 1343 | 1363 |
| LMArena Multi-Turn | 1371 | 1396 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than GPT-6 Luna?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 38.9 on the Noometry Index.
Which is cheaper, GLM-4.5-Air or GPT-6 Luna?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.
Is GLM-4.5-Air or GPT-6 Luna better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 131K.
How many benchmarks do GLM-4.5-Air and GPT-6 Luna share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GPT-6 Luna has 42.