Model comparison
Llama 2-70B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 24.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 2-70B scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 8.1.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | Yi-Lightning | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 24.4 | 37.1 |
| Released | 2023-07-18 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-70B leads
Llama 2-70B: 31.4 (#286), Yi-Lightning: 27.4 (#320)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1079 | 1312 |
| Aider Polyglot | — | 12.9% |
Reasoning Yi-Lightning leads
Llama 2-70B: 14.4 (#325), Yi-Lightning: 25.9 (#139)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1302 |
| 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-Lightning leads
Llama 2-70B: 8.1 (#326), Yi-Lightning: 36.2 (#172)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1091 | 1300 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Yi-Lightning leads
Llama 2-70B: 7.4 (#310), Yi-Lightning: 35.4 (#185)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1039 | 1286 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Yi-Lightning leads
Llama 2-70B: 27.7 (#274), Yi-Lightning: 42.2 (#196)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1045 | 1269 |
| LMArena Chinese | 995 | 1320 |
| LMArena French | 1090 | 1305 |
| LMArena German | 1041 | 1267 |
| LMArena Japanese | 927 | 1228 |
| LMArena Korean | 964 | 1192 |
| LMArena Russian | 1083 | 1255 |
| LMArena Spanish | 1143 | 1315 |
Instruction Following Yi-Lightning leads
Llama 2-70B: 54.9 (#278), Yi-Lightning: 67.4 (#196)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1071 | 1278 |
Long Context Yi-Lightning leads
Llama 2-70B: 32.3 (#270), Yi-Lightning: 39.4 (#181)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1062 | 1297 |
Writing & Preference Yi-Lightning leads
Llama 2-70B: 32.3 (#279), Yi-Lightning: 50.2 (#184)
| Benchmark | Llama 2-70B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1115 | 1302 |
| LMArena Creative Writing | 1075 | 1280 |
| LMArena Multi-Turn | 1088 | 1311 |
Frequently asked questions
Is Llama 2-70B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 24.4 on the Noometry Index.
Is Llama 2-70B or Yi-Lightning better for coding?
Llama 2-70B scores higher on coding benchmarks: 31.4 versus 27.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Yi-Lightning share?
17 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Yi-Lightning has 18.