Model comparison
Hunyuan Vision 1.5 vs Llama 2-70B
Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Tencent
MetaSummary
- They share 8 benchmarks with published results for both. Hunyuan Vision 1.5 scores higher in 6 categories and Llama 2-70B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hunyuan Vision 1.5 leads 60.1 to 32.3.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Hunyuan Vision 1.5 | Llama 2-70B | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 43.1 | 24.4 |
| Released | — | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Vision 1.5 leads
Hunyuan Vision 1.5: 41.8 (#119), Llama 2-70B: 31.4 (#286)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1418 | 1079 |
Reasoning Hunyuan Vision 1.5 leads
Hunyuan Vision 1.5: 28.9 (#97), Llama 2-70B: 14.4 (#325)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.79 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Not comparable
Hunyuan Vision 1.5: —, Llama 2-70B: 8.1 (#326)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0% |
| LMArena Math | — | 1091 |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Not comparable
Hunyuan Vision 1.5: —, Llama 2-70B: 7.4 (#310)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| GPQA Diamond | — | 26.3% |
| LMArena Expert | — | 1039 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multimodal Not comparable
Hunyuan Vision 1.5: 35.7 (#84), Llama 2-70B: —
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| LMArena Vision | 1180 | — |
Multilingual Hunyuan Vision 1.5 leads
Hunyuan Vision 1.5: 50.3 (#125), Llama 2-70B: 27.7 (#274)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1382 | 1045 |
| LMArena Chinese | — | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |
Instruction Following Hunyuan Vision 1.5 leads
Hunyuan Vision 1.5: 73.7 (#117), Llama 2-70B: 54.9 (#278)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1071 |
Long Context Hunyuan Vision 1.5 leads
Hunyuan Vision 1.5: 42.9 (#115), Llama 2-70B: 32.3 (#270)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1404 | 1062 |
Writing & Preference Hunyuan Vision 1.5 leads
Hunyuan Vision 1.5: 60.1 (#100), Llama 2-70B: 32.3 (#279)
| Benchmark | Hunyuan Vision 1.5 | Llama 2-70B |
|---|---|---|
| LMArena Text | 1405 | 1115 |
| LMArena Creative Writing | 1388 | 1075 |
| LMArena Multi-Turn | 1422 | 1088 |
Frequently asked questions
Is Hunyuan Vision 1.5 better than Llama 2-70B?
Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 24.4 on the Noometry Index.
Is Hunyuan Vision 1.5 or Llama 2-70B better for coding?
Hunyuan Vision 1.5 scores higher on coding benchmarks: 41.8 versus 31.4 in the Noometry coding category.
How many benchmarks do Hunyuan Vision 1.5 and Llama 2-70B share?
8 benchmarks have published results for both models. Hunyuan Vision 1.5 has 9 scored results on Noometry and Llama 2-70B has 35.