Model comparison
Gemma 2 9B vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 25.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
GoogleSummary
- They share 17 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and GLM-4.5-Air in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.5-Air leads 34.6 to 9.7.
Side by side
| Gemma 2 9B | GLM-4.5-Air | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 25.7 | 38.7 |
| Released | 2024-06-24 | 2025-07-20 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 98K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.10 |
| Results tracked | 35 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
Gemma 2 9B: 29.0 (#299), GLM-4.5-Air: 34.5 (#225)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1174 | 1397 |
| GSO | — | 2.9% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning GLM-4.5-Air leads
Gemma 2 9B: 15.3 (#306), GLM-4.5-Air: 23.3 (#166)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1379 |
| Kagi LLM Benchmark | — | 43% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.78 | — |
| ForecastBench | — | 59.2 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math GLM-4.5-Air leads
Gemma 2 9B: 9.3 (#312), GLM-4.5-Air: 33.8 (#166)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1183 | 1396 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| Omni-MATH | — | 39.1% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge GLM-4.5-Air leads
Gemma 2 9B: 9.7 (#300), GLM-4.5-Air: 34.6 (#184)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Expert | 1147 | 1370 |
| GPQA Diamond | 27.5% | — |
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual GLM-4.5-Air leads
Gemma 2 9B: 36.8 (#233), GLM-4.5-Air: 49.4 (#130)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1188 | 1366 |
| LMArena Chinese | 1185 | 1427 |
| LMArena French | 1189 | 1399 |
| LMArena German | 1186 | 1376 |
| LMArena Japanese | 1144 | 1348 |
| LMArena Korean | 1137 | 1306 |
| LMArena Russian | 1200 | 1373 |
| LMArena Spanish | 1200 | 1385 |
Instruction Following GLM-4.5-Air leads
Gemma 2 9B: 57.8 (#264), GLM-4.5-Air: 69.8 (#165)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1178 | 1353 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 81.2% |
Long Context GLM-4.5-Air leads
Gemma 2 9B: 36.3 (#228), GLM-4.5-Air: 41.6 (#130)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1197 | 1367 |
Writing & Preference GLM-4.5-Air leads
Gemma 2 9B: 32.3 (#276), GLM-4.5-Air: 56.1 (#134)
| Benchmark | Gemma 2 9B | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1207 | 1384 |
| LMArena Creative Writing | 1206 | 1343 |
| LMArena Multi-Turn | 1193 | 1371 |
| EQ-Bench Creative Writing | 841 | — |
| WildBench | — | 78.9% |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 25.7 on the Noometry Index.
Is Gemma 2 9B or GLM-4.5-Air better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 34.5 versus 29.0 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and GLM-4.5-Air share?
17 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GLM-4.5-Air has 27.