Model comparison
Llama 2-70B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 24.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Yi-1.5-34B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-1.5-34B leads 27.5 to 8.1.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 25.5% for Yi-1.5-34B.
Side by side
| Llama 2-70B | Yi-1.5-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 24.4 | 30.6 |
| Released | 2023-07-18 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Llama 2-70B: 31.4 (#286), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1079 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Reasoning Yi-1.5-34B leads
Llama 2-70B: 14.4 (#325), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1160 |
| 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 Yi-1.5-34B leads
Llama 2-70B: 8.1 (#326), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1091 | 1182 |
| MATH Level 5 | 3.3% | 25.5% |
| OTIS Mock AIME 2024-2025 | 0% | — |
| GSM8K | 69.6% | — |
Knowledge Yi-1.5-34B leads
Llama 2-70B: 7.4 (#310), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 26.3% | 32% |
| LMArena Expert | 1039 | 1144 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Yi-1.5-34B leads
Llama 2-70B: 27.7 (#274), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1045 | 1121 |
| LMArena Chinese | 995 | 1213 |
| LMArena French | 1090 | 1156 |
| LMArena German | 1041 | 1111 |
| LMArena Japanese | 927 | 1021 |
| LMArena Korean | 964 | 1005 |
| LMArena Russian | 1083 | 1091 |
| LMArena Spanish | 1143 | 1121 |
Instruction Following Yi-1.5-34B leads
Llama 2-70B: 54.9 (#278), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1071 | 1139 |
Long Context Yi-1.5-34B leads
Llama 2-70B: 32.3 (#270), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1062 | 1143 |
Writing & Preference Yi-1.5-34B leads
Llama 2-70B: 32.3 (#279), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Llama 2-70B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1115 | 1173 |
| LMArena Creative Writing | 1075 | 1135 |
| LMArena Multi-Turn | 1088 | 1153 |
Frequently asked questions
Is Llama 2-70B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 24.4 on the Noometry Index.
Is Llama 2-70B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 32.4 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Yi-1.5-34B share?
19 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Yi-1.5-34B has 21.