Model comparison
GPT-4.5 vs Llama 13b
GPT-4.5 is the stronger model overall, scoring 37.2 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
MetaSummary
- They share 9 benchmarks with published results for both. GPT-4.5 scores higher in 5 categories and Llama 13b in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 56.9 to 13.8.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Llama 13b | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 37.2 | 24.4 |
| Released | 2025-02-27 | 2023-02-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 42.2 (#109), Llama 13b: 21.4 (#337)
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| LMArena Coding | 1396 | 683 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Llama 13b: —
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Too close to call
GPT-4.5: 13.9 (#330), Llama 13b: 14.0 (#329)
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1403 | 728 |
| Epoch Capabilities Index | 136.74 | 100.58 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| BIG-Bench Hard | — | 37.9% |
| ForecastBench | 61.7 | — |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| LiveBench | 69% | — |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math GPT-4.5 leads
GPT-4.5: 32.6 (#211), Llama 13b: 26.7 (#256)
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| LMArena Math | 1412 | 838 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
GPT-4.5: 32.5 (#211), Llama 13b: —
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
| LMArena Expert | 1394 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
GPT-4.5: 37.6 (#71), Llama 13b: —
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
| ScienceQA | — | 43.3% |
Multilingual GPT-4.5 leads
GPT-4.5: 52.5 (#83), Llama 13b: 16.6 (#297)
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| LMArena Non-English | 1413 | 819 |
| LMArena Chinese | 1421 | — |
| LMArena French | 1418 | — |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |
| LMArena Russian | 1419 | — |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.6 (#134), Llama 13b: 36.7 (#305)
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1404 | 781 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Not comparable
GPT-4.5: 40.4 (#155), Llama 13b: —
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| Fiction.LiveBench | 63.9% | — |
| LMArena Longer Query | 1406 | — |
Writing & Preference GPT-4.5 leads
GPT-4.5: 56.9 (#134), Llama 13b: 13.8 (#312)
| Benchmark | GPT-4.5 | Llama 13b |
|---|---|---|
| LMArena Text | 1417 | 834 |
| LMArena Creative Writing | 1394 | 794 |
| LMArena Multi-Turn | 1444 | 753 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Llama 13b?
GPT-4.5 is the stronger model overall, scoring 37.2 to 24.4 on the Noometry Index.
Is GPT-4.5 or Llama 13b better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 21.4 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Llama 13b share?
9 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Llama 13b has 21.