Model comparison
Codellama 70b Instruct vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Yi-Lightning in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Yi-Lightning leads 42.2 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Yi-Lightning | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 33.7 | 37.1 |
| Released | — | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Yi-Lightning: 27.4 (#320)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| Aider Polyglot | — | 12.9% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1312 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Yi-Lightning leads
Codellama 70b Instruct: 20.1 (#242), Yi-Lightning: 25.9 (#139)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1302 |
Math Not comparable
Codellama 70b Instruct: —, Yi-Lightning: 36.2 (#172)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| LMArena Math | — | 1300 |
Knowledge Not comparable
Codellama 70b Instruct: —, Yi-Lightning: 35.4 (#185)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| LMArena Expert | — | 1286 |
Multilingual Yi-Lightning leads
Codellama 70b Instruct: 24.8 (#288), Yi-Lightning: 42.2 (#196)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 992 | 1269 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
Codellama 70b Instruct: 51.9 (#293), Yi-Lightning: 67.4 (#196)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1024 | 1278 |
Long Context Not comparable
Codellama 70b Instruct: —, Yi-Lightning: 39.4 (#181)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | — | 1297 |
Writing & Preference Yi-Lightning leads
Codellama 70b Instruct: 33.4 (#277), Yi-Lightning: 50.2 (#184)
| Benchmark | Codellama 70b Instruct | Yi-Lightning |
|---|---|---|
| LMArena Text | 1057 | 1302 |
| LMArena Creative Writing | — | 1280 |
| LMArena Multi-Turn | — | 1311 |
Frequently asked questions
Is Codellama 70b Instruct better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Yi-Lightning better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 27.4 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Yi-Lightning share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Yi-Lightning has 18.