Model comparison
Codellama 70b Instruct vs GPT-5.4 Pro
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 33.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 20.1.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | GPT-5.4 Pro | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.7 | 58.9 |
| Released | — | 2026-03-05 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $180 |
| Results tracked | 7 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
Codellama 70b Instruct: 37.6 (#193), GPT-5.4 Pro: 43.2 (#90)
| Benchmark | Codellama 70b Instruct | GPT-5.4 Pro |
|---|---|---|
| WeirdML | — | 57.4% |
| BigCodeBench Instruct | 40.7% | — |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning GPT-5.4 Pro leads
Codellama 70b Instruct: 20.1 (#242), GPT-5.4 Pro: 70.7 (#13)
| Benchmark | Codellama 70b Instruct | GPT-5.4 Pro |
|---|---|---|
| ARC-AGI-2 | — | 83.3% |
| SimpleBench | — | 74.1% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 58.6% |
| EnigmaEval | — | 23.8% |
| LMArena Hard Prompts | 1052 | — |
| Epoch Capabilities Index | — | 158.93 |
Math Not comparable
Codellama 70b Instruct: —, GPT-5.4 Pro: 72.4 (#22)
| Benchmark | Codellama 70b Instruct | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |
Knowledge Not comparable
Codellama 70b Instruct: —, GPT-5.4 Pro: 68.3 (#7)
| Benchmark | Codellama 70b Instruct | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | — | 94.6% |
| Humanity's Last Exam | — | 44.3% |
| SimpleQA Verified | — | 46.3% |
| Vectara Hallucination Rate | — | 8.3% |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), GPT-5.4 Pro: —
| Benchmark | Codellama 70b Instruct | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 51.9 (#293), GPT-5.4 Pro: —
| Benchmark | Codellama 70b Instruct | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.4 (#277), GPT-5.4 Pro: —
| Benchmark | Codellama 70b Instruct | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than GPT-5.4 Pro?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or GPT-5.4 Pro better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and GPT-5.4 Pro share?
0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-5.4 Pro has 16.