Model comparison
Claude 2 vs Codellama 34b Instruct
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 25.0 on the Noometry Index.
Last verified . 1 shared benchmarks.
MetaSummary
- They share 1 benchmark with published results for both. Claude 2 scores higher in 1 category and Codellama 34b Instruct in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 9.3.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Codellama 34b Instruct | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.0 | 30.8 |
| Released | 2023-07-11 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Codellama 34b Instruct: 28.5 (#314)
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| HumanEval+ | 61.6% | 43.9% |
| BigCodeBench Instruct | — | 29% |
| LMArena Coding | — | 1046 |
| BigCodeBench Complete | — | 37.1% |
| MBPP+ | — | 56.3% |
Reasoning Claude 2 leads
Claude 2: 21.7 (#216), Codellama 34b Instruct: 19.6 (#255)
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1032 |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.13 | — |
Math Codellama 34b Instruct leads
Claude 2: 9.3 (#320), Codellama 34b Instruct: 31.0 (#230)
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 1056 |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
Claude 2: 16.9 (#287), Codellama 34b Instruct: —
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| GPQA Diamond | 34.7% | — |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Multilingual Not comparable
Claude 2: —, Codellama 34b Instruct: 25.8 (#284)
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| LMArena Non-English | — | 1011 |
| LMArena Chinese | — | 976 |
Instruction Following Not comparable
Claude 2: —, Codellama 34b Instruct: 52.2 (#291)
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1028 |
Long Context Not comparable
Claude 2: —, Codellama 34b Instruct: 30.9 (#284)
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1013 |
Writing & Preference Not comparable
Claude 2: —, Codellama 34b Instruct: 28.2 (#297)
| Benchmark | Claude 2 | Codellama 34b Instruct |
|---|---|---|
| LMArena Text | — | 1066 |
| LMArena Creative Writing | — | 1032 |
| LMArena Multi-Turn | — | 1015 |
Frequently asked questions
Is Claude 2 better than Codellama 34b Instruct?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and Codellama 34b Instruct share?
1 benchmark has published results for both models. Claude 2 has 8 scored results on Noometry and Codellama 34b Instruct has 14.