Model comparison
Deepseek Coder v2 vs Hunyuan Turbo 0110
Hunyuan Turbo 0110 is the stronger model overall, scoring 39.6 to 35.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
TencentSummary
- They share 11 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Hunyuan Turbo 0110 in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hunyuan Turbo 0110 leads 50.2 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Hunyuan Turbo 0110 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 35.9 | 39.6 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Deepseek Coder v2: 38.1 (#183), Hunyuan Turbo 0110: 38.6 (#171)
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Coding | 1251 | 1319 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Hunyuan Turbo 0110 leads
Deepseek Coder v2: 23.6 (#176), Hunyuan Turbo 0110: 26.1 (#137)
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1308 |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 34.9 (#190), Hunyuan Turbo 0110: 35.6 (#180)
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Math | 1241 | 1273 |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Hunyuan Turbo 0110: —
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Hunyuan Turbo 0110 leads
Deepseek Coder v2: 36.3 (#240), Hunyuan Turbo 0110: 43.3 (#184)
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Non-English | 1182 | 1285 |
| LMArena Chinese | 1201 | 1358 |
| LMArena Russian | 1188 | 1305 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Hunyuan Turbo 0110 leads
Deepseek Coder v2: 61.7 (#242), Hunyuan Turbo 0110: 67.4 (#195)
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1278 |
Long Context Hunyuan Turbo 0110 leads
Deepseek Coder v2: 37.0 (#224), Hunyuan Turbo 0110: 39.8 (#168)
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Longer Query | 1219 | 1309 |
Writing & Preference Hunyuan Turbo 0110 leads
Deepseek Coder v2: 38.2 (#253), Hunyuan Turbo 0110: 50.2 (#183)
| Benchmark | Deepseek Coder v2 | Hunyuan Turbo 0110 |
|---|---|---|
| LMArena Text | 1191 | 1311 |
| LMArena Creative Writing | 1120 | 1269 |
| LMArena Multi-Turn | 1177 | 1303 |
Frequently asked questions
Is Deepseek Coder v2 better than Hunyuan Turbo 0110?
Hunyuan Turbo 0110 is the stronger model overall, scoring 39.6 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Hunyuan Turbo 0110 better for coding?
They score almost the same on coding (38.1 vs 38.6); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Hunyuan Turbo 0110 share?
11 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Hunyuan Turbo 0110 has 11.