Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs GLM-4.5V
GLM-4.5V has enough public results to be ranked (#158); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeekSide by side
| DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 39.7 | 39.2 |
| Released | 2024-05-07 | 2025-08-11 |
| Weights | Open | Open |
| Context window | — | 64K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $1.80 |
| Results tracked | 10 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141), GLM-4.5V: 38.9 (#152)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1347 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 26.5 (#118)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| Kagi LLM Benchmark | — | 59.8% |
| LMArena Hard Prompts | — | 1335 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 34.7 (#157)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| LMArena Math | — | 1353 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 36.8 (#155)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| LMArena Expert | — | 1353 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multimodal Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 33.6 (#86)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| LMArena Vision | — | 1154 |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 44.9 (#172)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| LMArena Non-English | — | 1304 |
| LMArena Chinese | — | 1338 |
| LMArena Russian | — | 1299 |
| LMArena Spanish | — | 1335 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 69.4 (#170)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| LMArena Instruction Following | — | 1311 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 39.6 (#166)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| LMArena Longer Query | — | 1305 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GLM-4.5V: 52.7 (#162)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GLM-4.5V |
|---|---|---|
| LMArena Text | — | 1333 |
| LMArena Creative Writing | — | 1295 |
| LMArena Multi-Turn | — | 1333 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than GLM-4.5V?
GLM-4.5V has enough public results to be ranked (#158); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or GLM-4.5V better for coding?
They score almost the same on coding (39.8 vs 38.9); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and GLM-4.5V share?
0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and GLM-4.5V has 15.