Model comparison
Deepseek Coder v2 vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 35.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GLM-5V-Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5V-Turbo leads 62.6 to 38.4.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | GLM-5V-Turbo | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 35.3 | 43.1 |
| Released | 2024-06-17 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.20 |
| Output $ / M tokens | — | $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
Deepseek Coder v2: 37.5 (#178), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1251 | 1467 |
| LMArena WebDev | — | 1400 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning GLM-5V-Turbo leads
Deepseek Coder v2: 22.6 (#175), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1443 |
| WinoGrande | 83.7% | — |
Math GLM-5V-Turbo leads
Deepseek Coder v2: 32.3 (#188), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1241 | 1440 |
| GSM8K | 94.5% | — |
Knowledge GLM-5V-Turbo leads
Deepseek Coder v2: 31.7 (#209), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1181 | 1451 |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual GLM-5V-Turbo leads
Deepseek Coder v2: 36.4 (#235), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1182 | 1420 |
| LMArena Chinese | 1201 | 1488 |
| LMArena French | 1184 | 1443 |
| LMArena German | 1164 | 1422 |
| LMArena Korean | 1104 | 1399 |
| LMArena Russian | 1188 | 1432 |
| LMArena Spanish | 1153 | 1446 |
| LMArena Japanese | 1126 | — |
Instruction Following GLM-5V-Turbo leads
Deepseek Coder v2: 61.9 (#237), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1180 | 1422 |
Long Context GLM-5V-Turbo leads
Deepseek Coder v2: 37.0 (#219), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1219 | 1439 |
Writing & Preference GLM-5V-Turbo leads
Deepseek Coder v2: 38.4 (#249), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | Deepseek Coder v2 | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1191 | 1437 |
| LMArena Creative Writing | 1120 | 1414 |
| LMArena Multi-Turn | 1176 | 1432 |
Frequently asked questions
Is Deepseek Coder v2 better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 35.3 on the Noometry Index.
Is Deepseek Coder v2 or GLM-5V-Turbo better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 41.8 versus 37.5 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and GLM-5V-Turbo share?
16 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GLM-5V-Turbo has 19.