Model comparison
GLM-4.5-Air vs Granite 4.2 3b
GLM-4.5-Air and Granite 4.2 3b score almost the same on the Noometry Index (38.9 vs 39.4), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GLM-4.5-Air scores higher in 4 categories and Granite 4.2 3b in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 47.2.
Side by side
| GLM-4.5-Air | Granite 4.2 3b | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 38.9 | 39.4 |
| Released | 2025-07-20 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 3b leads
GLM-4.5-Air: 33.3 (#259), Granite 4.2 3b: 40.0 (#151)
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| LMArena Coding | 1397 | 1361 |
| GSO | 2.9% | — |
Reasoning Granite 4.2 3b leads
GLM-4.5-Air: 24.1 (#166), Granite 4.2 3b: 26.0 (#138)
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1306 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math Not comparable
GLM-4.5-Air: 36.2 (#170), Granite 4.2 3b: —
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| Omni-MATH | 39.1% | — |
| LMArena Math | 1396 | — |
Knowledge Granite 4.2 3b leads
GLM-4.5-Air: 35.0 (#191), Granite 4.2 3b: 36.3 (#171)
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| LMArena Expert | 1370 | 1315 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Granite 4.2 3b: 42.1 (#198)
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| LMArena Non-English | 1366 | 1268 |
| LMArena Chinese | 1426 | 1269 |
| LMArena Russian | 1373 | 1249 |
| LMArena French | 1399 | — |
| LMArena German | 1377 | — |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1386 | — |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Granite 4.2 3b: 67.1 (#200)
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| LMArena Instruction Following | 1354 | 1273 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Granite 4.2 3b: 39.2 (#185)
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| LMArena Longer Query | 1366 | 1291 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Granite 4.2 3b: 47.2 (#212)
| Benchmark | GLM-4.5-Air | Granite 4.2 3b |
|---|---|---|
| LMArena Text | 1384 | 1293 |
| LMArena Creative Writing | 1343 | 1205 |
| LMArena Multi-Turn | 1371 | 1290 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Granite 4.2 3b?
GLM-4.5-Air and Granite 4.2 3b score almost the same on the Noometry Index (38.9 vs 39.4), so choose on price, context window or the category you care about most.
Is GLM-4.5-Air or Granite 4.2 3b better for coding?
Granite 4.2 3b scores higher on coding benchmarks: 40.0 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Granite 4.2 3b share?
11 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Granite 4.2 3b has 11.