Model comparison
DeepSeek-V2.5 (Sep 2024) vs Hunyuan Turbo 0110
Hunyuan Turbo 0110 is the stronger model overall, scoring 39.6 to 37.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
TencentSummary
- They share 11 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 2 categories and Hunyuan Turbo 0110 in 5 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Hunyuan Turbo 0110 leads 38.6 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 Turbo 0110 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 37.6 | 39.6 |
| Released | 2024-09-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Turbo 0110 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Hunyuan Turbo 0110: 38.6 (#171)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Coding | 1309 | 1319 |
| 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 Turbo 0110: 26.1 (#137)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1308 |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Hunyuan Turbo 0110: 35.6 (#180)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Math | 1288 | 1273 |
Knowledge Not comparable
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Hunyuan Turbo 0110: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Expert | 1266 | — |
Multilingual Too close to call
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Hunyuan Turbo 0110: 43.3 (#184)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Non-English | 1273 | 1285 |
| LMArena Chinese | 1318 | 1358 |
| LMArena Russian | 1289 | 1305 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Too close to call
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Hunyuan Turbo 0110: 67.4 (#195)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1278 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Hunyuan Turbo 0110: 39.8 (#168)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Longer Query | 1301 | 1309 |
Writing & Preference Too close to call
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Hunyuan Turbo 0110: 50.2 (#183)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Text | 1294 | 1311 |
| LMArena Creative Writing | 1285 | 1269 |
| LMArena Multi-Turn | 1297 | 1303 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Hunyuan Turbo 0110?
Hunyuan Turbo 0110 is the stronger model overall, scoring 39.6 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Hunyuan Turbo 0110 better for coding?
Hunyuan Turbo 0110 scores higher on coding benchmarks: 38.6 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Hunyuan Turbo 0110 share?
11 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Hunyuan Turbo 0110 has 11.