Model comparison
Gemma 7B vs GLM-4.7
GLM-4.7 is the stronger model overall, scoring 41.7 to 29.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
GoogleSummary
- They share 14 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and GLM-4.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.7 leads 61.1 to 27.2.
Side by side
| Gemma 7B | GLM-4.7 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 29.5 | 41.7 |
| Released | 2024-02-21 | 2025-12-22 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 27 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
Gemma 7B: 29.9 (#290), GLM-4.7: 43.6 (#74)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1048 | 1454 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| ALE-Bench | — | 399.48 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 7B: —, GLM-4.7: 26.4 (#96)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Vending-Bench 2 | — | 2,377 |
Reasoning GLM-4.7 leads
Gemma 7B: 19.0 (#247), GLM-4.7: 23.7 (#161)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1443 |
| Epoch Capabilities Index | 111.74 | 143.53 |
| SimpleBench | — | 47.7% |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math GLM-4.7 leads
Gemma 7B: 28.7 (#225), GLM-4.7: 37.7 (#92)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Math | 1066 | 1423 |
| OTIS Mock AIME 2024-2025 | — | 83.3% |
| ProofBench | — | 6% |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
| GSM8K | 46.4% | — |
Knowledge GLM-4.7 leads
Gemma 7B: 26.8 (#248), GLM-4.7: 47.0 (#74)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Expert | 1002 | 1424 |
| GPQA Diamond | — | 83.3% |
| SimpleQA Verified | — | 32.2% |
| Vectara Hallucination Rate | — | 11.7% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual GLM-4.7 leads
Gemma 7B: 25.3 (#282), GLM-4.7: 53.0 (#75)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 999 | 1417 |
| LMArena Chinese | 1035 | 1495 |
| LMArena French | 1024 | 1432 |
| LMArena Russian | 993 | 1423 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1439 |
| LMArena Korean | — | 1401 |
| LMArena Spanish | — | 1433 |
Instruction Following GLM-4.7 leads
Gemma 7B: 51.7 (#290), GLM-4.7: 74.6 (#90)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1411 |
Long Context GLM-4.7 leads
Gemma 7B: 31.1 (#277), GLM-4.7: 42.8 (#111)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1022 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
Writing & Preference GLM-4.7 leads
Gemma 7B: 27.2 (#297), GLM-4.7: 61.1 (#89)
| Benchmark | Gemma 7B | GLM-4.7 |
|---|---|---|
| LMArena Text | 1056 | 1436 |
| LMArena Creative Writing | 1024 | 1401 |
| LMArena Multi-Turn | 963 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |
Frequently asked questions
Is Gemma 7B better than GLM-4.7?
GLM-4.7 is the stronger model overall, scoring 41.7 to 29.5 on the Noometry Index.
Is Gemma 7B or GLM-4.7 better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 29.9 in the Noometry coding category.
How many benchmarks do Gemma 7B and GLM-4.7 share?
14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and GLM-4.7 has 36.