Model comparison
Llama 13b 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 . 8 shared benchmarks.
MetaSummary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Yi-1.5-34B in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-1.5-34B leads 37.4 to 13.8.
Side by side
| Llama 13b | Yi-1.5-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 24.4 | 30.6 |
| Released | 2023-02-24 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Llama 13b: 21.4 (#337), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 683 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Reasoning Yi-1.5-34B leads
Llama 13b: 14.0 (#329), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1160 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Too close to call
Llama 13b: 26.7 (#256), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 838 | 1182 |
| MATH Level 5 | — | 25.5% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Yi-1.5-34B: 14.8 (#295)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | — | 32% |
| LMArena Expert | — | 1144 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Yi-1.5-34B: —
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Yi-1.5-34B leads
Llama 13b: 16.6 (#297), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 819 | 1121 |
| LMArena Chinese | — | 1213 |
| LMArena French | — | 1156 |
| LMArena German | — | 1111 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Russian | — | 1091 |
| LMArena Spanish | — | 1121 |
Instruction Following Yi-1.5-34B leads
Llama 13b: 36.7 (#305), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 781 | 1139 |
Long Context Not comparable
Llama 13b: —, Yi-1.5-34B: 34.6 (#248)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | — | 1143 |
Writing & Preference Yi-1.5-34B leads
Llama 13b: 13.8 (#312), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Llama 13b | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 834 | 1173 |
| LMArena Creative Writing | 794 | 1135 |
| LMArena Multi-Turn | 753 | 1153 |
Frequently asked questions
Is Llama 13b 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 13b or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 32.4 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Yi-1.5-34B share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Yi-1.5-34B has 21.