Model comparison
GLM-4.5-Air vs Granite 3.1 8b Instruct
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 32.4 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 7 categories and Granite 3.1 8b Instruct 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 35.5.
Side by side
| GLM-4.5-Air | Granite 3.1 8b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 38.9 | 32.4 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 8b Instruct leads
GLM-4.5-Air: 33.3 (#259), Granite 3.1 8b Instruct: 34.5 (#233)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Coding | 1397 | 1186 |
| GSO | 2.9% | — |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Granite 3.1 8b Instruct: 24.1 (#120)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Granite 3.1 8b Instruct: 22.1 (#207)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1145 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Granite 3.1 8b Instruct: 33.0 (#209)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | 1396 | 1152 |
| Omni-MATH | 39.1% | — |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Granite 3.1 8b Instruct: 31.1 (#220)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | 1370 | 1142 |
| 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 3.1 8b Instruct: 30.9 (#260)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | 1366 | 1099 |
| LMArena Chinese | 1426 | 1145 |
| LMArena Russian | 1373 | 1092 |
| 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 3.1 8b Instruct: 58.6 (#259)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1354 | 1131 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Granite 3.1 8b Instruct: 35.2 (#241)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | 1366 | 1162 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Granite 3.1 8b Instruct: 35.5 (#266)
| Benchmark | GLM-4.5-Air | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | 1384 | 1150 |
| LMArena Creative Writing | 1343 | 1129 |
| LMArena Multi-Turn | 1371 | 1108 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Granite 3.1 8b Instruct?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 32.4 on the Noometry Index.
Is GLM-4.5-Air or Granite 3.1 8b Instruct better for coding?
Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Granite 3.1 8b Instruct share?
12 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Granite 3.1 8b Instruct has 13.