Model comparison
Llama 2-7B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.1 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 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.2 to 28.0.
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-7B | Yi-Lightning | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 29.1 | 37.1 |
| Released | 2023-07-18 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-7B leads
Llama 2-7B: 29.2 (#307), Yi-Lightning: 27.4 (#320)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1002 | 1312 |
| Aider Polyglot | — | 12.9% |
Reasoning Yi-Lightning leads
Llama 2-7B: 15.7 (#312), Yi-Lightning: 25.9 (#139)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1302 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 99.06 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Yi-Lightning leads
Llama 2-7B: 30.7 (#233), Yi-Lightning: 36.2 (#172)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1042 | 1300 |
| GSM8K | 16.7% | — |
Knowledge Yi-Lightning leads
Llama 2-7B: 28.2 (#248), Yi-Lightning: 35.4 (#185)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1036 | 1286 |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Yi-Lightning: —
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Yi-Lightning leads
Llama 2-7B: 23.8 (#293), Yi-Lightning: 42.2 (#196)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 973 | 1269 |
| LMArena Chinese | 973 | 1320 |
| LMArena French | 970 | 1305 |
| LMArena German | 978 | 1267 |
| LMArena Russian | 995 | 1255 |
| LMArena Spanish | 1007 | 1315 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
Instruction Following Yi-Lightning leads
Llama 2-7B: 50.8 (#298), Yi-Lightning: 67.4 (#196)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1006 | 1278 |
Long Context Yi-Lightning leads
Llama 2-7B: 30.4 (#287), Yi-Lightning: 39.4 (#181)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 999 | 1297 |
Writing & Preference Yi-Lightning leads
Llama 2-7B: 28.0 (#298), Yi-Lightning: 50.2 (#184)
| Benchmark | Llama 2-7B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1053 | 1302 |
| LMArena Creative Writing | 1033 | 1280 |
| LMArena Multi-Turn | 1029 | 1311 |
Frequently asked questions
Is Llama 2-7B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.1 on the Noometry Index.
Is Llama 2-7B or Yi-Lightning better for coding?
Llama 2-7B scores higher on coding benchmarks: 29.2 versus 27.4 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Yi-Lightning share?
15 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Yi-Lightning has 18.