Model comparison
DeepSeek-V2.5 (Sep 2024) vs Hunyuan Vision 1.5
Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 37.6 on the Noometry Index.
Last verified . 8 shared benchmarks.
DeepSeek
TencentSummary
- They share 8 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) 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 49.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 37.6 | 43.1 |
| Released | 2024-09-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Vision 1.5 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Hunyuan Vision 1.5: 41.8 (#119)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Coding | 1309 | 1418 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Hunyuan Vision 1.5 leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Hunyuan Vision 1.5: 28.9 (#97)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1416 |
Math Not comparable
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Hunyuan Vision 1.5: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Math | 1288 | — |
Knowledge Not comparable
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Hunyuan Vision 1.5: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Expert | 1266 | — |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Hunyuan Vision 1.5: 35.7 (#84)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Vision | — | 1180 |
Multilingual Hunyuan Vision 1.5 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Hunyuan Vision 1.5: 50.3 (#125)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Non-English | 1273 | 1382 |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Hunyuan Vision 1.5 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Hunyuan Vision 1.5: 73.7 (#117)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1397 |
Long Context Hunyuan Vision 1.5 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Hunyuan Vision 1.5: 42.9 (#115)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Longer Query | 1301 | 1404 |
Writing & Preference Hunyuan Vision 1.5 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Hunyuan Vision 1.5: 60.1 (#100)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Vision 1.5 |
|---|---|---|
| LMArena Text | 1294 | 1405 |
| LMArena Creative Writing | 1285 | 1388 |
| LMArena Multi-Turn | 1297 | 1422 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Hunyuan Vision 1.5?
Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Hunyuan Vision 1.5 better for coding?
Hunyuan Vision 1.5 scores higher on coding benchmarks: 41.8 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Hunyuan Vision 1.5 share?
8 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Hunyuan Vision 1.5 has 9.