Model comparison
Codellama 34b Instruct vs GPT-5
GPT-5 is the stronger model overall, scoring 50.9 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 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 30.9.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | GPT-5 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.8 | 50.9 |
| Released | — | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 14 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
Codellama 34b Instruct: 28.5 (#314), GPT-5: 50.3 (#47)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Coding | 1046 | 1436 |
| SWE-bench Verified | — | 73.6% |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| LMArena WebDev | — | 1418 |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
| WeirdML | — | 60.7% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 1,162 |
| AlgoTune | — | 1.67 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, GPT-5: 33.1 (#56)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |
Reasoning GPT-5 leads
Codellama 34b Instruct: 19.6 (#255), GPT-5: 38.3 (#64)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1416 |
| ARC-AGI-2 | — | 9.9% |
| SimpleBench | — | 56.7% |
| Kagi LLM Benchmark | — | 72.7% |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
| Chess Puzzles | — | 37% |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| Mystery Game Puzzles | — | 23% |
| DTBench | — | 90.7% |
| LMCA | — | 40% |
| Epoch Capabilities Index | — | 150 |
| ForecastBench | — | 61.4 |
Math GPT-5 leads
Codellama 34b Instruct: 31.0 (#230), GPT-5: 55.0 (#44)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Math | 1056 | 1407 |
| FrontierMath (Tiers 1-3) | — | 55.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 91.4% |
| ProofBench | — | 18% |
| Omni-MATH | — | 64.7% |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge Not comparable
Codellama 34b Instruct: —, GPT-5: 56.6 (#43)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| GPQA Diamond | — | 86.2% |
| Humanity's Last Exam | — | 25.3% |
| SimpleQA Verified | — | 50.1% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| Vectara Hallucination Rate | — | 14.7% |
| GPQA (HELM) | — | 79.2% |
| LMArena Expert | — | 1419 |
Multimodal Not comparable
Codellama 34b Instruct: —, GPT-5: 46.8 (#13)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Vision | — | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |
Multilingual GPT-5 leads
Codellama 34b Instruct: 25.8 (#284), GPT-5: 51.4 (#110)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Non-English | 1011 | 1397 |
| LMArena Chinese | 976 | 1422 |
| LMArena French | — | 1410 |
| LMArena German | — | 1416 |
| LMArena Japanese | — | 1409 |
| LMArena Korean | — | 1360 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1399 |
Instruction Following GPT-5 leads
Codellama 34b Instruct: 52.2 (#291), GPT-5: 73.8 (#113)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1388 |
| IFEval | — | 87.5% |
Long Context GPT-5 leads
Codellama 34b Instruct: 30.9 (#284), GPT-5: 69.5 (#2)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1013 | 1399 |
| Fiction.LiveBench | — | 97.2% |
Writing & Preference GPT-5 leads
Codellama 34b Instruct: 28.2 (#297), GPT-5: 63.4 (#65)
| Benchmark | Codellama 34b Instruct | GPT-5 |
|---|---|---|
| LMArena Text | 1066 | 1406 |
| LMArena Creative Writing | 1032 | 1365 |
| LMArena Multi-Turn | 1015 | 1426 |
| Short-Story Creative Writing | — | 86% |
| EQ-Bench Creative Writing | — | 1627 |
| WildBench | — | 85.7% |
Frequently asked questions
Is Codellama 34b Instruct better than GPT-5?
GPT-5 is the stronger model overall, scoring 50.9 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or GPT-5 better for coding?
GPT-5 scores higher on coding benchmarks: 50.3 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and GPT-5 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GPT-5 has 69.