Model comparison
GPT-5.2 Pro vs Llama 13b
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 24.4 on the Noometry Index.
Last verified . 1 shared benchmarks.
MetaSummary
- They share 1 benchmark with published results for both. GPT-5.2 Pro scores higher in 2 categories and Llama 13b in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 26.7.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Llama 13b | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 52.3 | 24.4 |
| Released | 2025-12-11 | 2023-02-24 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $21 | — |
| Output $ / M tokens | $168 | — |
| Results tracked | 8 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Llama 13b: 21.4 (#337)
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| LMArena Coding | — | 683 |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Llama 13b: 14.0 (#329)
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| Epoch Capabilities Index | 155.4 | 100.58 |
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 728 |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Llama 13b: 26.7 (#256)
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| LMArena Math | — | 838 |
| FrontierMath Tier 4 (v1) | 31.3% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
GPT-5.2 Pro: —, Llama 13b: —
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
GPT-5.2 Pro: —, Llama 13b: —
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Not comparable
GPT-5.2 Pro: —, Llama 13b: 16.6 (#297)
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| LMArena Non-English | — | 819 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Llama 13b: 36.7 (#305)
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| LMArena Instruction Following | — | 781 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Llama 13b: 13.8 (#312)
| Benchmark | GPT-5.2 Pro | Llama 13b |
|---|---|---|
| LMArena Text | — | 834 |
| LMArena Creative Writing | — | 794 |
| LMArena Multi-Turn | — | 753 |
Frequently asked questions
Is GPT-5.2 Pro better than Llama 13b?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 24.4 on the Noometry Index.
How many benchmarks do GPT-5.2 Pro and Llama 13b share?
1 benchmark has published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Llama 13b has 21.