Model comparison
Claude 3 Opus vs Codellama 70b Instruct
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 29.3 on the Noometry Index.
Last verified . 7 shared benchmarks.
MetaSummary
- They share 7 benchmarks with published results for both. Claude 3 Opus scores higher in 3 categories and Codellama 70b Instruct in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Claude 3 Opus leads 41.6 to 24.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 57.4% for Claude 3 Opus and 49.6% for Codellama 70b Instruct.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Codellama 70b Instruct | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 29.3 | 33.3 |
| Released | 2024-02-29 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 46 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Claude 3 Opus: 32.4 (#261), Codellama 70b Instruct: 37.0 (#189)
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| BigCodeBench Instruct | 45.5% | 40.7% |
| BigCodeBench Complete | 57.4% | 49.6% |
| HumanEval+ | 77.4% | 65.9% |
| WeirdML | 19.2% | — |
| LiveBench Coding | 38.6% | — |
| LMArena Coding | 1264 | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Opus: 24.3 (#110), Codellama 70b Instruct: —
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Codellama 70b Instruct leads
Claude 3 Opus: 14.2 (#318), Codellama 70b Instruct: 19.2 (#241)
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1052 |
| SimpleBench | 23.5% | — |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| Epoch Capabilities Index | 126.91 | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Not comparable
Claude 3 Opus: 13.9 (#293), Codellama 70b Instruct: —
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | — |
| LiveBench Math | 43.6% | — |
| LMArena Math | 1273 | — |
| MATH Level 5 | 37.5% | — |
Knowledge Not comparable
Claude 3 Opus: 24.5 (#262), Codellama 70b Instruct: —
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| GPQA Diamond | 47.2% | — |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |
| LMArena Expert | 1223 | — |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 26.6 (#112), Codellama 70b Instruct: —
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Claude 3 Opus leads
Claude 3 Opus: 41.6 (#202), Codellama 70b Instruct: 24.9 (#283)
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| LMArena Non-English | 1258 | 992 |
| LMArena Chinese | 1248 | — |
| LMArena French | 1274 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1204 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1280 | — |
| LMArena Spanish | 1246 | — |
Instruction Following Claude 3 Opus leads
Claude 3 Opus: 64.3 (#223), Codellama 70b Instruct: 52.1 (#288)
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| LMArena Instruction Following | 1248 | 1024 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Not comparable
Claude 3 Opus: 38.2 (#197), Codellama 70b Instruct: —
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| LMArena Longer Query | 1259 | — |
Writing & Preference Claude 3 Opus leads
Claude 3 Opus: 47.4 (#208), Codellama 70b Instruct: 33.6 (#272)
| Benchmark | Claude 3 Opus | Codellama 70b Instruct |
|---|---|---|
| LMArena Text | 1262 | 1057 |
| LMArena Creative Writing | 1235 | — |
| LMArena Multi-Turn | 1275 | — |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Codellama 70b Instruct?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 29.3 on the Noometry Index.
Is Claude 3 Opus or Codellama 70b Instruct better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 32.4 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Codellama 70b Instruct share?
7 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Codellama 70b Instruct has 7.