Model comparison
Codellama 34b Instruct vs Yi-34B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 27.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Yi-34B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 21.6.
Side by side
| Codellama 34b Instruct | Yi-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 30.8 | 27.8 |
| Released | — | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Codellama 34b Instruct: 28.5 (#314), Yi-34B: 32.3 (#274)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| LMArena Coding | 1046 | 1112 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Yi-34B leads
Codellama 34b Instruct: 19.6 (#255), Yi-34B: 21.2 (#226)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Yi-34B: 21.6 (#282)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| LMArena Math | 1056 | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Not comparable
Codellama 34b Instruct: —, Yi-34B: 7.5 (#309)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| GPQA Diamond | — | 14.7% |
| LMArena Expert | — | 1061 |
| MMLU | — | 76.3% |
Multilingual Yi-34B leads
Codellama 34b Instruct: 25.8 (#284), Yi-34B: 29.7 (#264)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| LMArena Non-English | 1011 | 1079 |
| LMArena Chinese | 976 | 1176 |
| LMArena French | — | 1081 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Russian | — | 1050 |
| LMArena Spanish | — | 1070 |
Instruction Following Yi-34B leads
Codellama 34b Instruct: 52.2 (#291), Yi-34B: 56.2 (#274)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1091 |
Long Context Yi-34B leads
Codellama 34b Instruct: 30.9 (#284), Yi-34B: 33.2 (#264)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1013 | 1094 |
Writing & Preference Yi-34B leads
Codellama 34b Instruct: 28.2 (#297), Yi-34B: 34.1 (#273)
| Benchmark | Codellama 34b Instruct | Yi-34B |
|---|---|---|
| LMArena Text | 1066 | 1129 |
| LMArena Creative Writing | 1032 | 1108 |
| LMArena Multi-Turn | 1015 | 1113 |
Frequently asked questions
Is Codellama 34b Instruct better than Yi-34B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 27.8 on the Noometry Index.
Is Codellama 34b Instruct or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 32.3 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Yi-34B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Yi-34B has 23.