Model comparison
Codellama 70b Instruct vs GPT-4.1
GPT-4.1 is the stronger model overall, scoring 35.9 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and GPT-4.1 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4.1 leads 49.4 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | GPT-4.1 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.7 | 35.9 |
| Released | — | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 7 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), GPT-4.1: 34.4 (#238)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| WeirdML | — | 39% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1391 |
| BigCodeBench Complete | 49.6% | — |
| CadEval | — | 42% |
| ALE-Bench | — | 558.1 |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, GPT-4.1: 34.7 (#43)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), GPT-4.1: 11.7 (#339)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1384 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | — | 27% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| EnigmaEval | — | 2.2% |
| DTBench | — | 68.3% |
| LMCA | — | 25.6% |
| Epoch Capabilities Index | — | 136.78 |
| ForecastBench | — | 61.5 |
Math Not comparable
Codellama 70b Instruct: —, GPT-4.1: 22.3 (#280)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 6% |
| OTIS Mock AIME 2024-2025 | — | 38.3% |
| Omni-MATH | — | 47.1% |
| LMArena Math | — | 1370 |
| MATH Level 5 | — | 83% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
Codellama 70b Instruct: —, GPT-4.1: 37.1 (#160)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| GPQA Diamond | — | 66.9% |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | — | 31.1% |
| MMLU-Pro | — | 81.1% |
| Vectara Hallucination Rate | — | 5.6% |
| GPQA (HELM) | — | 65.9% |
| LMArena Expert | — | 1364 |
Multimodal Not comparable
Codellama 70b Instruct: —, GPT-4.1: 38.2 (#67)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| LMArena Vision | — | 1211 |
| GeoBench | — | 72% |
Multilingual GPT-4.1 leads
Codellama 70b Instruct: 24.8 (#288), GPT-4.1: 49.4 (#133)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 992 | 1370 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1382 |
| LMArena German | — | 1381 |
| LMArena Japanese | — | 1319 |
| LMArena Korean | — | 1339 |
| LMArena Russian | — | 1377 |
| LMArena Spanish | — | 1376 |
Instruction Following GPT-4.1 leads
Codellama 70b Instruct: 51.9 (#293), GPT-4.1: 71.3 (#153)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1367 |
| IFEval | — | 83.8% |
Long Context Not comparable
Codellama 70b Instruct: —, GPT-4.1: 40.0 (#163)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| Fiction.LiveBench | — | 63.9% |
| LMArena Longer Query | — | 1385 |
Writing & Preference GPT-4.1 leads
Codellama 70b Instruct: 33.4 (#277), GPT-4.1: 57.6 (#125)
| Benchmark | Codellama 70b Instruct | GPT-4.1 |
|---|---|---|
| LMArena Text | 1057 | 1383 |
| LMArena Creative Writing | — | 1363 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |
| LMArena Multi-Turn | — | 1398 |
Frequently asked questions
Is Codellama 70b Instruct better than GPT-4.1?
GPT-4.1 is the stronger model overall, scoring 35.9 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or GPT-4.1 better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 34.4 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and GPT-4.1 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-4.1 has 52.