Model comparison
DeepSeek-V2.5 (Sep 2024) vs Hunyuan T1 20250711
Hunyuan T1 20250711 is the stronger model overall, scoring 42.5 to 37.6 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
TencentSummary
- They share 13 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Hunyuan T1 20250711 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hunyuan T1 20250711 leads 59.5 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 T1 20250711 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 37.6 | 42.5 |
| 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 T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Hunyuan T1 20250711: 40.9 (#129)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Coding | 1309 | 1390 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Hunyuan T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Hunyuan T1 20250711: 28.5 (#103)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1399 |
Math Hunyuan T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Hunyuan T1 20250711: 38.7 (#130)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Math | 1288 | 1414 |
Knowledge Hunyuan T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Hunyuan T1 20250711: 38.8 (#141)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Expert | 1266 | 1395 |
Multilingual Hunyuan T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Hunyuan T1 20250711: 51.2 (#112)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Non-English | 1273 | 1395 |
| LMArena Chinese | 1318 | 1425 |
| LMArena Korean | 1209 | 1406 |
| LMArena Russian | 1289 | 1385 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Hunyuan T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Hunyuan T1 20250711: 72.6 (#138)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1374 |
Long Context Hunyuan T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Hunyuan T1 20250711: 42.2 (#128)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Longer Query | 1301 | 1384 |
Writing & Preference Hunyuan T1 20250711 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Hunyuan T1 20250711: 59.5 (#109)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Hunyuan T1 20250711 |
|---|---|---|
| LMArena Text | 1294 | 1401 |
| LMArena Creative Writing | 1285 | 1392 |
| LMArena Multi-Turn | 1297 | 1393 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Hunyuan T1 20250711?
Hunyuan T1 20250711 is the stronger model overall, scoring 42.5 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Hunyuan T1 20250711 better for coding?
Hunyuan T1 20250711 scores higher on coding benchmarks: 40.9 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Hunyuan T1 20250711 share?
13 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Hunyuan T1 20250711 has 13.