Model comparison
DeepSeek-V2.5 (Sep 2024) vs Hunyuan Turbos 20250226
Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 37.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeek
TencentSummary
- They share 16 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Hunyuan Turbos 20250226 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hunyuan Turbos 20250226 leads 40.0 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 Turbos 20250226 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 37.6 | 41.3 |
| Released | 2024-09-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Hunyuan Turbos 20250226: 40.0 (#152)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Coding | 1309 | 1361 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Hunyuan Turbos 20250226: 27.8 (#113)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1374 |
Math Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Hunyuan Turbos 20250226: 37.5 (#154)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Math | 1288 | 1359 |
Knowledge Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Hunyuan Turbos 20250226: 37.0 (#161)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Expert | 1266 | 1339 |
Multilingual Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Hunyuan Turbos 20250226: 48.9 (#136)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Non-English | 1273 | 1363 |
| LMArena Chinese | 1318 | 1417 |
| LMArena French | 1289 | 1391 |
| LMArena German | 1258 | 1355 |
| LMArena Japanese | 1228 | 1342 |
| LMArena Korean | 1209 | 1351 |
| LMArena Russian | 1289 | 1368 |
| LMArena Spanish | 1248 | — |
Instruction Following Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Hunyuan Turbos 20250226: 71.0 (#158)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1344 |
Long Context Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Hunyuan Turbos 20250226: 41.6 (#136)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Longer Query | 1301 | 1366 |
Writing & Preference Hunyuan Turbos 20250226 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Hunyuan Turbos 20250226: 57.4 (#128)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Text | 1294 | 1377 |
| LMArena Creative Writing | 1285 | 1359 |
| LMArena Multi-Turn | 1297 | 1387 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Hunyuan Turbos 20250226?
Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Hunyuan Turbos 20250226 better for coding?
Hunyuan Turbos 20250226 scores higher on coding benchmarks: 40.0 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Hunyuan Turbos 20250226 share?
16 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Hunyuan Turbos 20250226 has 16.