Model comparison
Llama 2-13B vs Yi-34B
Llama 2-13B is the stronger model overall, scoring 29.6 to 27.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Llama 2-13B scores higher in 2 categories and Yi-34B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-13B leads 28.1 to 7.5.
Side by side
| Llama 2-13B | Yi-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 29.6 | 27.8 |
| Released | 2023-07-18 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Llama 2-13B: 30.9 (#291), Yi-34B: 32.3 (#274)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Coding | 1062 | 1112 |
Reasoning Yi-34B leads
Llama 2-13B: 12.8 (#337), Yi-34B: 21.2 (#226)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1104 |
| BIG-Bench Hard | 58.2% | 71.7% |
| Epoch Capabilities Index | 106.17 | 117.39 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Llama 2-13B leads
Llama 2-13B: 31.1 (#229), Yi-34B: 21.6 (#282)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Math | 1065 | 1114 |
| GSM8K | 36.9% | 76% |
| MATH Level 5 | — | 5.1% |
Knowledge Llama 2-13B leads
Llama 2-13B: 28.1 (#249), Yi-34B: 7.5 (#309)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Expert | 1030 | 1061 |
| MMLU | 55.6% | 76.3% |
| GPQA Diamond | — | 14.7% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Yi-34B: —
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Yi-34B leads
Llama 2-13B: 26.5 (#279), Yi-34B: 29.7 (#264)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1024 | 1079 |
| LMArena Chinese | 1001 | 1176 |
| LMArena French | 1044 | 1081 |
| LMArena German | 1009 | 1042 |
| LMArena Japanese | 894 | 993 |
| LMArena Korean | 953 | 959 |
| LMArena Russian | 1055 | 1050 |
| LMArena Spanish | 1087 | 1070 |
Instruction Following Yi-34B leads
Llama 2-13B: 53.3 (#287), Yi-34B: 56.2 (#274)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1045 | 1091 |
Long Context Too close to call
Llama 2-13B: 32.3 (#269), Yi-34B: 33.2 (#264)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1064 | 1094 |
Writing & Preference Yi-34B leads
Llama 2-13B: 29.8 (#289), Yi-34B: 34.1 (#273)
| Benchmark | Llama 2-13B | Yi-34B |
|---|---|---|
| LMArena Text | 1084 | 1129 |
| LMArena Creative Writing | 1047 | 1108 |
| LMArena Multi-Turn | 1050 | 1113 |
Frequently asked questions
Is Llama 2-13B better than Yi-34B?
Llama 2-13B is the stronger model overall, scoring 29.6 to 27.8 on the Noometry Index.
Is Llama 2-13B or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 32.3 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Yi-34B share?
21 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Yi-34B has 23.