Model comparison
Codellama 34b Instruct vs GPT-5.6 Luna
GPT-5.6 Luna is the stronger model overall, scoring 54.6 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-5.6 Luna in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 31.0.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | GPT-5.6 Luna | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.8 | 54.6 |
| Released | — | 2026-07-09 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 14 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
Codellama 34b Instruct: 28.5 (#314), GPT-5.6 Luna: 54.5 (#28)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Coding | 1046 | 1466 |
| DeepSWE | — | 67.2% |
| FrontierCode | — | 39.8% |
| CursorBench | — | 35.9% |
| LMArena WebDev | — | 1519 |
| SciCode | — | 53.6% |
| WeirdML | — | 60.9% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 1,667 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, GPT-5.6 Luna: 34.4 (#45)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| APEX-Agents | — | 43% |
| BALROG | — | 45.6% |
| GDP.pdf | — | 22.7% |
| Vending-Bench 2 | — | 4,095 |
Reasoning GPT-5.6 Luna leads
Codellama 34b Instruct: 19.6 (#255), GPT-5.6 Luna: 47.6 (#43)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1451 |
| ARC-AGI-2 | — | 59.5% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 49.1% |
| NYT Connections (extended) | — | 69.4% |
| ARC-AGI-1 | — | 88% |
| CritPt | — | 20.6% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 21% |
| DTBench | — | 89.1% |
| LMCA | — | 48.5% |
| Surface Evolver Bench | — | 61.9% |
| Epoch Capabilities Index | — | 156.39 |
Math GPT-5.6 Luna leads
Codellama 34b Instruct: 31.0 (#230), GPT-5.6 Luna: 77.7 (#14)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Math | 1056 | 1458 |
| FrontierMath (Tiers 1-3) | — | 82.1% |
| FrontierMath Tier 4 | — | 61% |
| OTIS Mock AIME 2024-2025 | — | 98.3% |
| ProofBench | — | 60% |
Knowledge Not comparable
Codellama 34b Instruct: —, GPT-5.6 Luna: 58.5 (#34)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | — | 91.6% |
| SimpleQA Verified | — | 41% |
| LMArena Expert | — | 1478 |
Multimodal Not comparable
Codellama 34b Instruct: —, GPT-5.6 Luna: 42.7 (#28)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | — | 1258 |
| Blueprint-Bench 2 | — | 22.6% |
| Furniture Assembly | — | 42.5% |
| LMArena Document | — | 1457 |
Multilingual GPT-5.6 Luna leads
Codellama 34b Instruct: 25.8 (#284), GPT-5.6 Luna: 52.8 (#78)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1011 | 1417 |
| LMArena Chinese | 976 | 1470 |
| LMArena French | — | 1456 |
| LMArena German | — | 1454 |
| LMArena Japanese | — | 1411 |
| LMArena Korean | — | 1415 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1448 |
Instruction Following GPT-5.6 Luna leads
Codellama 34b Instruct: 52.2 (#291), GPT-5.6 Luna: 75.6 (#57)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1028 | 1437 |
Long Context GPT-5.6 Luna leads
Codellama 34b Instruct: 30.9 (#284), GPT-5.6 Luna: 43.9 (#82)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1013 | 1436 |
Writing & Preference GPT-5.6 Luna leads
Codellama 34b Instruct: 28.2 (#297), GPT-5.6 Luna: 68.0 (#29)
| Benchmark | Codellama 34b Instruct | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1066 | 1431 |
| LMArena Creative Writing | 1032 | 1396 |
| LMArena Multi-Turn | 1015 | 1434 |
| EQ-Bench Creative Writing | — | 1829 |
| EQ-Bench 4 | — | 1156 |
Frequently asked questions
Is Codellama 34b Instruct better than GPT-5.6 Luna?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or GPT-5.6 Luna better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and GPT-5.6 Luna share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GPT-5.6 Luna has 52.