Model comparison
Gemma 2B vs GLM-5.3
GLM-5.3 is the stronger model overall, scoring 54.8 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and GLM-5.3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.3 leads 75.7 to 24.0.
Side by side
| Gemma 2B | GLM-5.3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 29.6 | 54.8 |
| Released | 2024-02-21 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 23 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
Gemma 2B: 29.4 (#305), GLM-5.3: 59.5 (#14)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| LMArena Coding | 1010 | 1496 |
| DeepSWE | — | 69% |
| FrontierCode | — | 40.1% |
| CursorBench | — | 42.6% |
| LMArena WebDev | — | 1622 |
| FrontierSWE | — | 30.2% |
| SciCode | — | 59% |
| WeirdML | — | 75.4% |
| ALE-Bench | — | 1,317 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, GLM-5.3: 36.4 (#38)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| APEX-Agents | — | 56.6% |
| Vending-Bench 2 | — | 8,164 |
Reasoning GLM-5.3 leads
Gemma 2B: 18.8 (#275), GLM-5.3: 46.1 (#46)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| LMArena Hard Prompts | 989 | 1489 |
| Epoch Capabilities Index | 94.2 | 155.61 |
| NYT Connections (extended) | — | 74.2% |
| CritPt | — | 19.1% |
| Chess Puzzles | — | 21% |
| Mystery Game Puzzles | — | 33% |
| DTBench | — | 87.7% |
| LMCA | — | 55.5% |
| Bench to the Future 3 | — | 0.15 |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math GLM-5.3 leads
Gemma 2B: 30.0 (#239), GLM-5.3: 62.3 (#33)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| LMArena Math | 1009 | 1489 |
| FrontierMath (Tiers 1-3) | — | 68.8% |
| FrontierMath Tier 4 | — | 29.3% |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| ProofBench | — | 49% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, GLM-5.3: 58.3 (#37)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 41% |
| LMArena Expert | — | 1516 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual GLM-5.3 leads
Gemma 2B: 23.0 (#294), GLM-5.3: 55.7 (#28)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| LMArena Non-English | 958 | 1457 |
| LMArena Chinese | 986 | 1528 |
| LMArena Russian | 937 | 1463 |
| LMArena French | — | 1499 |
| LMArena German | — | 1499 |
| LMArena Japanese | — | 1453 |
| LMArena Korean | — | 1472 |
| LMArena Spanish | — | 1460 |
Instruction Following GLM-5.3 leads
Gemma 2B: 48.5 (#302), GLM-5.3: 77.5 (#23)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| LMArena Instruction Following | 970 | 1477 |
Long Context GLM-5.3 leads
Gemma 2B: 29.9 (#291), GLM-5.3: 45.4 (#41)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| LMArena Longer Query | 981 | 1482 |
Writing & Preference GLM-5.3 leads
Gemma 2B: 24.0 (#308), GLM-5.3: 75.7 (#6)
| Benchmark | Gemma 2B | GLM-5.3 |
|---|---|---|
| LMArena Text | 1002 | 1471 |
| LMArena Creative Writing | 987 | 1457 |
| LMArena Multi-Turn | 945 | 1472 |
| EQ-Bench Creative Writing | — | 2075 |
Frequently asked questions
Is Gemma 2B better than GLM-5.3?
GLM-5.3 is the stronger model overall, scoring 54.8 to 29.6 on the Noometry Index.
Is Gemma 2B or GLM-5.3 better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.5 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and GLM-5.3 share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and GLM-5.3 has 42.