Model comparison
DeepSeek LLM 67B vs Hunyuan Turbos 20250226
Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
TencentSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Hunyuan Turbos 20250226 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hunyuan Turbos 20250226 leads 37.0 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Hunyuan Turbos 20250226 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 24.9 | 41.3 |
| Released | 2023-11-29 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 31.9 (#278), Hunyuan Turbos 20250226: 40.0 (#152)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Coding | 1096 | 1361 |
Reasoning Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 16.5 (#304), Hunyuan Turbos 20250226: 27.8 (#113)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1374 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 8.7 (#324), Hunyuan Turbos 20250226: 37.5 (#154)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Math | 1108 | 1359 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 7.0 (#313), Hunyuan Turbos 20250226: 37.0 (#161)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1339 |
Multilingual Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 29.4 (#267), Hunyuan Turbos 20250226: 48.9 (#136)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Non-English | 1073 | 1363 |
| LMArena Chinese | 1132 | 1417 |
| LMArena French | — | 1391 |
| LMArena German | — | 1355 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1351 |
| LMArena Russian | — | 1368 |
Instruction Following Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 55.4 (#277), Hunyuan Turbos 20250226: 71.0 (#158)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1344 |
Long Context Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 33.1 (#265), Hunyuan Turbos 20250226: 41.6 (#136)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Longer Query | 1092 | 1366 |
Writing & Preference Hunyuan Turbos 20250226 leads
DeepSeek LLM 67B: 31.6 (#282), Hunyuan Turbos 20250226: 57.4 (#128)
| Benchmark | DeepSeek LLM 67B | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Text | 1105 | 1377 |
| LMArena Creative Writing | 1067 | 1359 |
| LMArena Multi-Turn | 1082 | 1387 |
Frequently asked questions
Is DeepSeek LLM 67B better than Hunyuan Turbos 20250226?
Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Hunyuan Turbos 20250226 better for coding?
Hunyuan Turbos 20250226 scores higher on coding benchmarks: 40.0 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Hunyuan Turbos 20250226 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Hunyuan Turbos 20250226 has 16.