Model comparison
Codellama 34b Instruct vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
NVIDIASummary
- They share 9 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Llama2 70b Steerlm Chat in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama2 70b Steerlm Chat leads 31.6 to 28.2.
Side by side
| Codellama 34b Instruct | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.8 | 31.8 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama2 70b Steerlm Chat leads
Codellama 34b Instruct: 28.5 (#314), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Codellama 34b Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1046 | 1025 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Codellama 34b Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1047 |
Math Too close to call
Codellama 34b Instruct: 31.0 (#230), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Codellama 34b Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1056 | 1072 |
Multilingual Llama2 70b Steerlm Chat leads
Codellama 34b Instruct: 25.8 (#284), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Codellama 34b Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1011 | 1063 |
| LMArena Chinese | 976 | — |
Instruction Following Llama2 70b Steerlm Chat leads
Codellama 34b Instruct: 52.2 (#291), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Codellama 34b Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1028 | 1060 |
Long Context Too close to call
Codellama 34b Instruct: 30.9 (#284), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Codellama 34b Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1013 | 998 |
Writing & Preference Llama2 70b Steerlm Chat leads
Codellama 34b Instruct: 28.2 (#297), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Codellama 34b Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1066 | 1098 |
| LMArena Creative Writing | 1032 | 1091 |
| LMArena Multi-Turn | 1015 | 1058 |
Frequently asked questions
Is Codellama 34b Instruct better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Llama2 70b Steerlm Chat better for coding?
Llama2 70b Steerlm Chat scores higher on coding benchmarks: 29.9 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Llama2 70b Steerlm Chat has 9.