Model comparison
Deepseek Coder v2 vs Hunyuan Vision 1.5
Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 35.9 on the Noometry Index.
Last verified . 8 shared benchmarks.
DeepSeek
TencentSummary
- They share 8 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Hunyuan Vision 1.5 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hunyuan Vision 1.5 leads 60.1 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Hunyuan Vision 1.5 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 35.9 | 43.1 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Vision 1.5 leads
Deepseek Coder v2: 38.1 (#183), Hunyuan Vision 1.5: 41.8 (#119)
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Coding | 1251 | 1418 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Hunyuan Vision 1.5 leads
Deepseek Coder v2: 23.6 (#176), Hunyuan Vision 1.5: 28.9 (#97)
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1416 |
| WinoGrande | 83.7% | — |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), Hunyuan Vision 1.5: —
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Hunyuan Vision 1.5: —
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Hunyuan Vision 1.5: 35.7 (#84)
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Vision | — | 1180 |
Multilingual Hunyuan Vision 1.5 leads
Deepseek Coder v2: 36.3 (#240), Hunyuan Vision 1.5: 50.3 (#125)
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Non-English | 1182 | 1382 |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Hunyuan Vision 1.5 leads
Deepseek Coder v2: 61.7 (#242), Hunyuan Vision 1.5: 73.7 (#117)
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1397 |
Long Context Hunyuan Vision 1.5 leads
Deepseek Coder v2: 37.0 (#224), Hunyuan Vision 1.5: 42.9 (#115)
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Longer Query | 1219 | 1404 |
Writing & Preference Hunyuan Vision 1.5 leads
Deepseek Coder v2: 38.2 (#253), Hunyuan Vision 1.5: 60.1 (#100)
| Benchmark | Deepseek Coder v2 | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Text | 1191 | 1405 |
| LMArena Creative Writing | 1120 | 1388 |
| LMArena Multi-Turn | 1177 | 1422 |
Frequently asked questions
Is Deepseek Coder v2 better than Hunyuan Vision 1.5?
Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Hunyuan Vision 1.5 better for coding?
Hunyuan Vision 1.5 scores higher on coding benchmarks: 41.8 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Hunyuan Vision 1.5 share?
8 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Hunyuan Vision 1.5 has 9.