Model comparison
GLM-4.5-Air vs Llama 4 Maverick
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. GLM-4.5-Air scores higher in 7 categories and Llama 4 Maverick in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 38.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 55.9% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
- GLM-4.5-Air accepts more context: 131K tokens versus 128K.
Side by side
| GLM-4.5-Air | Llama 4 Maverick | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 38.9 | 30.9 |
| Released | 2025-07-20 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 98K | 4K |
| Input $ / M tokens | $0.20 | $0.19 |
| Output $ / M tokens | $1.10 | $0.65 |
| Results tracked | 27 | 54 |
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: 33.3 (#259), Llama 4 Maverick: 26.6 (#324)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1397 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| GSO | 2.9% | — |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Llama 4 Maverick: 28.2 (#91)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Llama 4 Maverick: 10.1 (#342)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| Kagi LLM Benchmark | 43% | 55.9% |
| LMArena Hard Prompts | 1379 | 1281 |
| ForecastBench | 59.2 | 57.5 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| Epoch Capabilities Index | — | 132.2 |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Llama 4 Maverick: 26.0 (#262)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| Omni-MATH | 39.1% | 42.2% |
| LMArena Math | 1396 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Llama 4 Maverick: 33.4 (#204)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| Humanity's Last Exam | 8.1% | 5.7% |
| MMLU-Pro | 76.2% | 81% |
| Vectara Hallucination Rate | 9.3% | 8.2% |
| GPQA (HELM) | 59.4% | 65% |
| LMArena Expert | 1370 | 1259 |
| GPQA Diamond | — | 67% |
| Confabulations | — | 22.6% |
Multimodal Not comparable
GLM-4.5-Air: —, Llama 4 Maverick: 31.6 (#105)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Llama 4 Maverick: 42.2 (#195)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1366 | 1269 |
| LMArena Chinese | 1426 | 1277 |
| LMArena French | 1399 | 1259 |
| LMArena German | 1377 | 1291 |
| LMArena Japanese | 1348 | 1207 |
| LMArena Korean | 1308 | 1203 |
| LMArena Russian | 1373 | 1286 |
| LMArena Spanish | 1386 | 1293 |
Instruction Following Llama 4 Maverick leads
GLM-4.5-Air: 69.6 (#171), Llama 4 Maverick: 71.7 (#146)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| IFEval | 81.2% | 90.8% |
| LMArena Instruction Following | 1354 | 1267 |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Llama 4 Maverick: 31.4 (#279)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1366 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Llama 4 Maverick: 38.8 (#252)
| Benchmark | GLM-4.5-Air | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1384 | 1287 |
| LMArena Creative Writing | 1343 | 1267 |
| WildBench | 78.9% | 80% |
| LMArena Multi-Turn | 1371 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
Frequently asked questions
Is GLM-4.5-Air better than Llama 4 Maverick?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.9 on the Noometry Index.
Which is cheaper, GLM-4.5-Air or Llama 4 Maverick?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.
Is GLM-4.5-Air or Llama 4 Maverick better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 26.6 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 Llama 4 Maverick share?
26 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Llama 4 Maverick has 54.