Model comparison
Codellama 70b Instruct vs GPT-5.2 Pro
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 33.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.8 to 19.2.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | GPT-5.2 Pro | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.3 | 52.2 |
| Released | — | 2025-12-11 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $21 |
| Output $ / M tokens | — | $168 |
| Results tracked | 7 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codellama 70b Instruct: 37.0 (#189), GPT-5.2 Pro: —
| Benchmark | Codellama 70b Instruct | GPT-5.2 Pro |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning GPT-5.2 Pro leads
Codellama 70b Instruct: 19.2 (#241), GPT-5.2 Pro: 51.8 (#31)
| Benchmark | Codellama 70b Instruct | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | — | 54.2% |
| SimpleBench | — | 57.4% |
| NYT Connections (extended) | — | 79.3% |
| ARC-AGI-1 | — | 90.5% |
| LMArena Hard Prompts | 1052 | — |
| Epoch Capabilities Index | — | 155.41 |
Math Not comparable
Codellama 70b Instruct: —, GPT-5.2 Pro: 64.8 (#23)
| Benchmark | Codellama 70b Instruct | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| FrontierMath Tier 4 (v1) | — | 31.3% |
Multilingual Not comparable
Codellama 70b Instruct: 24.9 (#283), GPT-5.2 Pro: —
| Benchmark | Codellama 70b Instruct | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 52.1 (#288), GPT-5.2 Pro: —
| Benchmark | Codellama 70b Instruct | GPT-5.2 Pro |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.6 (#272), GPT-5.2 Pro: —
| Benchmark | Codellama 70b Instruct | GPT-5.2 Pro |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than GPT-5.2 Pro?
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 33.3 on the Noometry Index.
How many benchmarks do Codellama 70b Instruct and GPT-5.2 Pro share?
0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-5.2 Pro has 8.