Model comparison
Codellama 70b Instruct vs o3-pro
o3-pro is the stronger model overall, scoring 42.7 to 33.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in writing & preference, where o3-pro leads 57.1 to 33.6.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | o3-pro | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.3 | 42.7 |
| Released | — | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 7 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Codellama 70b Instruct: 37.0 (#189), o3-pro: 55.1 (#22)
| Benchmark | Codellama 70b Instruct | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| BigCodeBench Instruct | 40.7% | — |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning o3-pro leads
Codellama 70b Instruct: 19.2 (#241), o3-pro: 24.1 (#152)
| Benchmark | Codellama 70b Instruct | o3-pro |
|---|---|---|
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| LMArena Hard Prompts | 1052 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.43 |
Knowledge Not comparable
Codellama 70b Instruct: —, o3-pro: 29.0 (#234)
| Benchmark | Codellama 70b Instruct | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
Multilingual Not comparable
Codellama 70b Instruct: 24.9 (#283), o3-pro: —
| Benchmark | Codellama 70b Instruct | o3-pro |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 52.1 (#288), o3-pro: —
| Benchmark | Codellama 70b Instruct | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Long Context Not comparable
Codellama 70b Instruct: —, o3-pro: 72.1 (#1)
| Benchmark | Codellama 70b Instruct | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
Writing & Preference o3-pro leads
Codellama 70b Instruct: 33.6 (#272), o3-pro: 57.1 (#128)
| Benchmark | Codellama 70b Instruct | o3-pro |
|---|---|---|
| LMArena Text | 1057 | — |
| Short-Story Creative Writing | — | 84.4% |
Frequently asked questions
Is Codellama 70b Instruct better than o3-pro?
o3-pro is the stronger model overall, scoring 42.7 to 33.3 on the Noometry Index.
Is Codellama 70b Instruct or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.1 versus 37.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and o3-pro share?
0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and o3-pro has 12.