Model comparison
Gemma 3 12B vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 31.8 on the Noometry Index. Gemma 3 12B costs 25× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and GLM-5V-Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5V-Turbo leads 36.6 to 21.0.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- GLM-5V-Turbo accepts more context: 200K tokens versus 131K.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 12B | GLM-5V-Turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 31.8 | 43.1 |
| Released | 2025-03-12 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | 131K | 200K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.05 | $1.20 |
| Output $ / M tokens | $0.15 | $4 |
| Results tracked | 24 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
Gemma 3 12B: 31.2 (#276), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1281 | 1467 |
| LMArena WebDev | — | 1400 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), GLM-5V-Turbo: —
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning GLM-5V-Turbo leads
Gemma 3 12B: 15.2 (#307), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1443 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math GLM-5V-Turbo leads
Gemma 3 12B: 21.0 (#273), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1307 | 1440 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge GLM-5V-Turbo leads
Gemma 3 12B: 26.5 (#250), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1248 | 1451 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
| MindCube | 46.7% | — |
Multilingual GLM-5V-Turbo leads
Gemma 3 12B: 45.9 (#160), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1318 | 1420 |
| LMArena German | 1370 | 1422 |
| LMArena Russian | 1335 | 1432 |
| LMArena Chinese | — | 1488 |
| LMArena French | — | 1443 |
| LMArena Korean | — | 1399 |
| LMArena Spanish | — | 1446 |
Instruction Following GLM-5V-Turbo leads
Gemma 3 12B: 68.8 (#179), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1299 | 1422 |
Long Context GLM-5V-Turbo leads
Gemma 3 12B: 40.0 (#157), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1317 | 1439 |
Writing & Preference GLM-5V-Turbo leads
Gemma 3 12B: 47.7 (#205), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | Gemma 3 12B | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1334 | 1437 |
| LMArena Creative Writing | 1331 | 1414 |
| LMArena Multi-Turn | 1334 | 1432 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 31.8 on the Noometry Index. Gemma 3 12B costs 25× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 12B or GLM-5V-Turbo?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is Gemma 3 12B or GLM-5V-Turbo better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 41.8 versus 31.2 in the Noometry coding category.
Which has the bigger context window?
GLM-5V-Turbo does, with 200K tokens against 131K.
How many benchmarks do Gemma 3 12B and GLM-5V-Turbo share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and GLM-5V-Turbo has 19.