Model comparison
GLM-4.5-Air vs Granite 3.1 2b Instruct
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 32.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Granite 3.1 2b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 56.1 to 34.3.
Side by side
| GLM-4.5-Air | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 38.7 | 32.6 |
| 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 | 12 |
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: 34.5 (#225), Granite 3.1 2b Instruct: 32.9 (#255)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1397 | 1149 |
| GSO | 2.9% | — |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 23.3 (#166), Granite 3.1 2b Instruct: 21.0 (#206)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1138 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 33.8 (#166), Granite 3.1 2b Instruct: 30.6 (#206)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1396 | 1159 |
| Omni-MATH | 39.1% | — |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 34.6 (#184), Granite 3.1 2b Instruct: 30.3 (#223)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1370 | 1131 |
| 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: 49.4 (#130), Granite 3.1 2b Instruct: 29.2 (#264)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1366 | 1068 |
| LMArena Chinese | 1427 | 1138 |
| LMArena Russian | 1373 | 1063 |
| LMArena French | 1399 | — |
| LMArena German | 1376 | — |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1306 | — |
| LMArena Spanish | 1385 | — |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.8 (#165), Granite 3.1 2b Instruct: 58.0 (#259)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1353 | 1116 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#130), Granite 3.1 2b Instruct: 35.0 (#239)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1367 | 1155 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 56.1 (#134), Granite 3.1 2b Instruct: 34.3 (#269)
| Benchmark | GLM-4.5-Air | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1384 | 1127 |
| LMArena Creative Writing | 1343 | 1116 |
| LMArena Multi-Turn | 1371 | 1099 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Granite 3.1 2b Instruct?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 32.6 on the Noometry Index.
Is GLM-4.5-Air or Granite 3.1 2b Instruct better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 34.5 versus 32.9 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Granite 3.1 2b Instruct has 12.