Model comparison
Gemma 2B vs GLM-4.6
GLM-4.6 is the stronger model overall, scoring 41.4 to 29.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
GoogleSummary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and GLM-4.6 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 24.0.
Side by side
| Gemma 2B | GLM-4.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 29.6 | 41.4 |
| Released | 2024-02-21 | 2025-09-30 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 23 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
Gemma 2B: 29.4 (#305), GLM-4.6: 40.1 (#148)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1010 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| ALE-Bench | — | 340.82 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, GLM-4.6: 32.3 (#66)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning GLM-4.6 leads
Gemma 2B: 18.8 (#275), GLM-4.6: 23.7 (#172)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 989 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math GLM-4.6 leads
Gemma 2B: 30.0 (#239), GLM-4.6: 39.1 (#111)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| LMArena Math | 1009 | 1432 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, GLM-4.6: 40.2 (#124)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | — | 9.5% |
| LMArena Expert | — | 1431 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual GLM-4.6 leads
Gemma 2B: 23.0 (#294), GLM-4.6: 53.5 (#66)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 958 | 1426 |
| LMArena Chinese | 986 | 1499 |
| LMArena Russian | 937 | 1419 |
| LMArena French | — | 1459 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1393 |
| LMArena Korean | — | 1400 |
| LMArena Spanish | — | 1436 |
Instruction Following GLM-4.6 leads
Gemma 2B: 48.5 (#302), GLM-4.6: 74.3 (#98)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 970 | 1410 |
Long Context GLM-4.6 leads
Gemma 2B: 29.9 (#291), GLM-4.6: 43.4 (#94)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 981 | 1422 |
Writing & Preference GLM-4.6 leads
Gemma 2B: 24.0 (#308), GLM-4.6: 61.1 (#90)
| Benchmark | Gemma 2B | GLM-4.6 |
|---|---|---|
| LMArena Text | 1002 | 1440 |
| LMArena Creative Writing | 987 | 1411 |
| LMArena Multi-Turn | 945 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |
Frequently asked questions
Is Gemma 2B better than GLM-4.6?
GLM-4.6 is the stronger model overall, scoring 41.4 to 29.6 on the Noometry Index.
Is Gemma 2B 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 2B and GLM-4.6 share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and GLM-4.6 has 29.