Model comparison
Gemma 7B vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 30.0 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-5.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 66.9 to 27.1.
Side by side
| Gemma 7B | GLM-5.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 30.0 | 47.8 |
| Released | 2024-02-21 | 2026-04-07 |
| Weights | Open | Open |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 27 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
Gemma 7B: 30.5 (#294), GLM-5.1: 48.7 (#55)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Coding | 1048 | 1485 |
| SWE-bench Verified | — | 74.2% |
| LMArena WebDev | — | 1508 |
| SciCode | — | 43.8% |
| WeirdML | — | 57.1% |
| ALE-Bench | — | 887.1 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 7B: —, GLM-5.1: 24.9 (#113)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| APEX-Agents | — | 40.9% |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
Gemma 7B: 19.9 (#249), GLM-5.1: 39.1 (#60)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1472 |
| Epoch Capabilities Index | 111.99 | 149.84 |
| SimpleBench | — | 55.1% |
| NYT Connections (extended) | — | 77.7% |
| CritPt | — | 4.6% |
| Chess Puzzles | — | 19% |
| Thematic Generalization | — | 69.8% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math GLM-5.1 leads
Gemma 7B: 31.2 (#228), GLM-5.1: 49.7 (#60)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Math | 1066 | 1473 |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 22.2% |
| FrontierMath (Feb 2025 set) | — | 33.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
| GSM8K | 46.4% | — |
Knowledge GLM-5.1 leads
Gemma 7B: 27.3 (#252), GLM-5.1: 54.9 (#50)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Expert | 1001 | 1476 |
| GPQA Diamond | — | 89.9% |
| SimpleQA Verified | — | 34% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual GLM-5.1 leads
Gemma 7B: 25.1 (#287), GLM-5.1: 55.0 (#36)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 999 | 1447 |
| LMArena Chinese | 1035 | 1515 |
| LMArena French | 1025 | 1474 |
| LMArena Russian | 993 | 1454 |
| LMArena German | — | 1465 |
| LMArena Japanese | — | 1434 |
| LMArena Korean | — | 1418 |
| LMArena Spanish | — | 1469 |
Instruction Following GLM-5.1 leads
Gemma 7B: 51.5 (#295), GLM-5.1: 76.3 (#42)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1451 |
Long Context GLM-5.1 leads
Gemma 7B: 31.1 (#282), GLM-5.1: 44.9 (#53)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1022 | 1466 |
Writing & Preference GLM-5.1 leads
Gemma 7B: 27.1 (#302), GLM-5.1: 66.9 (#31)
| Benchmark | Gemma 7B | GLM-5.1 |
|---|---|---|
| LMArena Text | 1056 | 1461 |
| LMArena Creative Writing | 1024 | 1453 |
| LMArena Multi-Turn | 963 | 1472 |
| EQ-Bench Creative Writing | — | 1592 |
Frequently asked questions
Is Gemma 7B better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 30.0 on the Noometry Index.
Is Gemma 7B or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and GLM-5.1 share?
14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and GLM-5.1 has 41.