Model comparison
Codellama 34b Instruct vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and GPT-5.2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.2 leads 66.8 to 28.2.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | GPT-5.2 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.8 | 54.1 |
| Released | — | 2025-12-11 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 14 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
Codellama 34b Instruct: 28.5 (#314), GPT-5.2: 51.6 (#37)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Coding | 1046 | 1447 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1416 |
| SWE-bench Multilingual | — | 66.7% |
| GSO | — | 27.4% |
| WeirdML | — | 72.2% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, GPT-5.2: 40.2 (#24)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| Terminal-Bench | — | 64.9% |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |
| Vending-Bench 2 | — | 3,591 |
Reasoning GPT-5.2 leads
Codellama 34b Instruct: 19.6 (#255), GPT-5.2: 50.2 (#35)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1445 |
| ARC-AGI-2 | — | 52.9% |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | — | 73.3% |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
| Chess Puzzles | — | 49% |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| Mystery Game Puzzles | — | 23% |
| DTBench | — | 90.9% |
| LMCA | — | 43.9% |
| Epoch Capabilities Index | — | 153.45 |
| ForecastBench | — | 60.1 |
Math GPT-5.2 leads
Codellama 34b Instruct: 31.0 (#230), GPT-5.2: 60.0 (#38)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Math | 1056 | 1440 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 15% |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge Not comparable
Codellama 34b Instruct: —, GPT-5.2: 59.3 (#32)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| GPQA Diamond | — | 91.4% |
| Humanity's Last Exam | — | 27.8% |
| SimpleQA Verified | — | 37.1% |
| Vectara Hallucination Rate | — | 8.4% |
| LMArena Expert | — | 1445 |
Multimodal Not comparable
Codellama 34b Instruct: —, GPT-5.2: 51.3 (#7)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Vision | — | 1268 |
| VPCT | — | 84% |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |
Multilingual GPT-5.2 leads
Codellama 34b Instruct: 25.8 (#284), GPT-5.2: 53.4 (#67)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1011 | 1425 |
| LMArena Chinese | 976 | 1460 |
| LMArena French | — | 1455 |
| LMArena German | — | 1448 |
| LMArena Japanese | — | 1420 |
| LMArena Korean | — | 1392 |
| LMArena Russian | — | 1440 |
| LMArena Spanish | — | 1433 |
Instruction Following GPT-5.2 leads
Codellama 34b Instruct: 52.2 (#291), GPT-5.2: 74.7 (#89)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1417 |
Long Context GPT-5.2 leads
Codellama 34b Instruct: 30.9 (#284), GPT-5.2: 44.0 (#78)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1013 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
Codellama 34b Instruct: 28.2 (#297), GPT-5.2: 66.8 (#32)
| Benchmark | Codellama 34b Instruct | GPT-5.2 |
|---|---|---|
| LMArena Text | 1066 | 1439 |
| LMArena Creative Writing | 1032 | 1401 |
| LMArena Multi-Turn | 1015 | 1458 |
| EQ-Bench Creative Writing | — | 1703 |
Frequently asked questions
Is Codellama 34b Instruct better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and GPT-5.2 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GPT-5.2 has 67.