Model comparison
Gemma 2 9B vs GLM-4.6
GLM-4.6 is the stronger model overall, scoring 41.4 to 25.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and GLM-4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6 leads 40.2 to 9.7.
Side by side
| Gemma 2 9B | GLM-4.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 25.9 | 41.4 |
| Released | 2024-06-24 | 2025-09-30 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 35 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
Gemma 2 9B: 29.4 (#304), GLM-4.6: 40.1 (#148)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1173 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, GLM-4.6: 32.3 (#66)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning GLM-4.6 leads
Gemma 2 9B: 15.9 (#309), GLM-4.6: 23.7 (#172)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math GLM-4.6 leads
Gemma 2 9B: 9.9 (#318), GLM-4.6: 39.1 (#111)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Math | 1183 | 1432 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 84.9% | — |
Knowledge GLM-4.6 leads
Gemma 2 9B: 9.7 (#305), GLM-4.6: 40.2 (#124)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1147 | 1431 |
| GPQA Diamond | 27.5% | — |
| Vectara Hallucination Rate | — | 9.5% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual GLM-4.6 leads
Gemma 2 9B: 36.6 (#238), GLM-4.6: 53.5 (#66)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1188 | 1426 |
| LMArena Chinese | 1185 | 1499 |
| LMArena French | 1190 | 1459 |
| LMArena German | 1186 | 1447 |
| LMArena Japanese | 1144 | 1393 |
| LMArena Korean | 1137 | 1400 |
| LMArena Russian | 1200 | 1419 |
| LMArena Spanish | 1200 | 1436 |
Instruction Following GLM-4.6 leads
Gemma 2 9B: 57.6 (#269), GLM-4.6: 74.3 (#98)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1178 | 1410 |
| LiveBench Instruction Following | 52.6% | — |
Long Context GLM-4.6 leads
Gemma 2 9B: 36.3 (#233), GLM-4.6: 43.4 (#94)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1197 | 1422 |
Writing & Preference GLM-4.6 leads
Gemma 2 9B: 32.1 (#281), GLM-4.6: 61.1 (#90)
| Benchmark | Gemma 2 9B | GLM-4.6 |
|---|---|---|
| LMArena Text | 1207 | 1440 |
| LMArena Creative Writing | 1206 | 1411 |
| EQ-Bench Creative Writing | 841 | 1411 |
| LMArena Multi-Turn | 1193 | 1427 |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than GLM-4.6?
GLM-4.6 is the stronger model overall, scoring 41.4 to 25.9 on the Noometry Index.
Is Gemma 2 9B or GLM-4.6 better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and GLM-4.6 share?
18 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GLM-4.6 has 29.