Model comparison
Hunyuan T1 20250711 vs Llama 3-70B
Hunyuan T1 20250711 is the stronger model overall, scoring 42.5 to 28.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Tencent
MetaSummary
- They share 13 benchmarks with published results for both. Hunyuan T1 20250711 scores higher in 8 categories and Llama 3-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hunyuan T1 20250711 leads 38.7 to 12.8.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Hunyuan T1 20250711 | Llama 3-70B | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 42.5 | 28.8 |
| Released | — | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 40.9 (#129), Llama 3-70B: 35.8 (#218)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1390 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Hunyuan T1 20250711: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 28.5 (#103), Llama 3-70B: 18.0 (#288)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 38.7 (#130), Llama 3-70B: 12.8 (#305)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Math | 1414 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 38.8 (#141), Llama 3-70B: 20.8 (#277)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1395 | 1149 |
| GPQA Diamond | — | 40.6% |
| MMLU | — | 79.3% |
Multilingual Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 51.2 (#112), Llama 3-70B: 33.6 (#251)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1395 | 1142 |
| LMArena Chinese | 1425 | 1114 |
| LMArena Korean | 1406 | 1017 |
| LMArena Russian | 1385 | 1159 |
| LMArena French | — | 1232 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Spanish | — | 1241 |
Instruction Following Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 72.6 (#138), Llama 3-70B: 62.5 (#238)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1374 | 1194 |
Long Context Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 42.2 (#128), Llama 3-70B: 35.6 (#240)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1384 | 1174 |
Writing & Preference Hunyuan T1 20250711 leads
Hunyuan T1 20250711: 59.5 (#109), Llama 3-70B: 42.8 (#231)
| Benchmark | Hunyuan T1 20250711 | Llama 3-70B |
|---|---|---|
| LMArena Text | 1401 | 1221 |
| LMArena Creative Writing | 1392 | 1210 |
| LMArena Multi-Turn | 1393 | 1223 |
Frequently asked questions
Is Hunyuan T1 20250711 better than Llama 3-70B?
Hunyuan T1 20250711 is the stronger model overall, scoring 42.5 to 28.8 on the Noometry Index.
Is Hunyuan T1 20250711 or Llama 3-70B better for coding?
Hunyuan T1 20250711 scores higher on coding benchmarks: 40.9 versus 35.8 in the Noometry coding category.
How many benchmarks do Hunyuan T1 20250711 and Llama 3-70B share?
13 benchmarks have published results for both models. Hunyuan T1 20250711 has 13 scored results on Noometry and Llama 3-70B has 31.