Model comparison
Deepseek Coder v2 vs GLM-4.5V
GLM-4.5V is the stronger model overall, scoring 39.8 to 35.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeekSummary
- They share 13 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GLM-4.5V in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5V leads 52.5 to 38.2.
Side by side
| Deepseek Coder v2 | GLM-4.5V | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 35.9 | 39.8 |
| Released | 2024-06-17 | 2025-08-11 |
| Weights | Open | Open |
| Context window | — | 64K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $1.80 |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5V leads
Deepseek Coder v2: 38.1 (#183), GLM-4.5V: 39.5 (#155)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Coding | 1251 | 1347 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning GLM-4.5V leads
Deepseek Coder v2: 23.6 (#176), GLM-4.5V: 27.4 (#119)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1334 |
| Kagi LLM Benchmark | — | 59.8% |
| WinoGrande | 83.7% | — |
Math GLM-4.5V leads
Deepseek Coder v2: 34.9 (#190), GLM-4.5V: 37.4 (#159)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Math | 1241 | 1354 |
| GSM8K | 94.5% | — |
Knowledge GLM-4.5V leads
Deepseek Coder v2: 32.3 (#212), GLM-4.5V: 37.5 (#156)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Expert | 1181 | 1353 |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, GLM-4.5V: 34.3 (#92)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Vision | — | 1154 |
Multilingual GLM-4.5V leads
Deepseek Coder v2: 36.3 (#240), GLM-4.5V: 44.6 (#177)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Non-English | 1182 | 1303 |
| LMArena Chinese | 1201 | 1337 |
| LMArena Russian | 1188 | 1298 |
| LMArena Spanish | 1153 | 1336 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
Instruction Following GLM-4.5V leads
Deepseek Coder v2: 61.7 (#242), GLM-4.5V: 69.2 (#175)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Instruction Following | 1180 | 1311 |
Long Context GLM-4.5V leads
Deepseek Coder v2: 37.0 (#224), GLM-4.5V: 39.6 (#171)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Longer Query | 1219 | 1304 |
Writing & Preference GLM-4.5V leads
Deepseek Coder v2: 38.2 (#253), GLM-4.5V: 52.5 (#170)
| Benchmark | Deepseek Coder v2 | GLM-4.5V |
|---|---|---|
| LMArena Text | 1191 | 1333 |
| LMArena Creative Writing | 1120 | 1295 |
| LMArena Multi-Turn | 1177 | 1332 |
Frequently asked questions
Is Deepseek Coder v2 better than GLM-4.5V?
GLM-4.5V is the stronger model overall, scoring 39.8 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or GLM-4.5V better for coding?
GLM-4.5V scores higher on coding benchmarks: 39.5 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and GLM-4.5V share?
13 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GLM-4.5V has 15.