Model comparison
DeepSeek-V2.5 (Sep 2024) vs Hunyuan Large Vision
DeepSeek-V2.5 (Sep 2024) and Hunyuan Large Vision score almost the same on the Noometry Index (37.6 vs 37.6), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
DeepSeek
TencentSummary
- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Hunyuan Large Vision in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hunyuan Large Vision leads 38.3 to 31.7.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 37.6 | 37.6 |
| Released | 2024-09-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Large Vision leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Hunyuan Large Vision: 38.3 (#180)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Coding | 1309 | 1308 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Too close to call
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Hunyuan Large Vision: 24.8 (#158)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1257 |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Hunyuan Large Vision: 35.5 (#183)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Math | 1288 | 1268 |
Knowledge Too close to call
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Hunyuan Large Vision: 34.4 (#196)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Expert | 1266 | 1252 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Hunyuan Large Vision: 35.7 (#83)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Vision | — | 1180 |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Hunyuan Large Vision: 39.9 (#221)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Non-English | 1273 | 1236 |
| LMArena Chinese | 1318 | 1287 |
| LMArena Russian | 1289 | 1243 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Hunyuan Large Vision: 65.8 (#215)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Instruction Following | 1280 | 1251 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Hunyuan Large Vision: 38.9 (#189)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Longer Query | 1301 | 1280 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Hunyuan Large Vision: 46.5 (#218)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Large Vision |
|---|---|---|
| LMArena Text | 1294 | 1263 |
| LMArena Creative Writing | 1285 | 1248 |
| LMArena Multi-Turn | 1297 | 1254 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Hunyuan Large Vision?
DeepSeek-V2.5 (Sep 2024) and Hunyuan Large Vision score almost the same on the Noometry Index (37.6 vs 37.6), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or Hunyuan Large Vision better for coding?
Hunyuan Large Vision scores higher on coding benchmarks: 38.3 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Hunyuan Large Vision share?
12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Hunyuan Large Vision has 13.