Model comparison
Llama 2-7B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 28.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
MetaSummary
- They share 15 benchmarks with published results for both. Llama 2-7B scores higher in 2 categories and Yi-1.5-34B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-7B leads 27.7 to 14.8.
Side by side
| Llama 2-7B | Yi-1.5-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 28.6 | 30.2 |
| Released | 2023-07-18 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Llama 2-7B: 28.7 (#302), Yi-1.5-34B: 31.9 (#267)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1002 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Reasoning Yi-1.5-34B leads
Llama 2-7B: 15.1 (#309), Yi-1.5-34B: 21.5 (#195)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1160 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 98.54 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Llama 2-7B leads
Llama 2-7B: 28.2 (#231), Yi-1.5-34B: 25.3 (#248)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1042 | 1182 |
| MATH Level 5 | — | 25.5% |
| GSM8K | 16.7% | — |
Knowledge Llama 2-7B leads
Llama 2-7B: 27.7 (#243), Yi-1.5-34B: 14.8 (#290)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Expert | 1036 | 1144 |
| GPQA Diamond | — | 32% |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Yi-1.5-34B: —
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Yi-1.5-34B leads
Llama 2-7B: 23.9 (#288), Yi-1.5-34B: 32.5 (#251)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 973 | 1121 |
| LMArena Chinese | 973 | 1213 |
| LMArena French | 969 | 1155 |
| LMArena German | 978 | 1111 |
| LMArena Russian | 995 | 1091 |
| LMArena Spanish | 1007 | 1120 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
Instruction Following Yi-1.5-34B leads
Llama 2-7B: 51.0 (#293), Yi-1.5-34B: 59.4 (#252)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1006 | 1139 |
Long Context Yi-1.5-34B leads
Llama 2-7B: 30.4 (#282), Yi-1.5-34B: 34.6 (#243)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 999 | 1144 |
Writing & Preference Yi-1.5-34B leads
Llama 2-7B: 28.1 (#293), Yi-1.5-34B: 37.6 (#252)
| Benchmark | Llama 2-7B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1053 | 1173 |
| LMArena Creative Writing | 1033 | 1135 |
| LMArena Multi-Turn | 1029 | 1153 |
Frequently asked questions
Is Llama 2-7B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 28.6 on the Noometry Index.
Is Llama 2-7B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 31.9 versus 28.7 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Yi-1.5-34B share?
15 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Yi-1.5-34B has 21.