Model comparison
GPT-6 Sol vs Llama 3.2 90B
GPT-6 Sol is the stronger model overall, scoring 49.2 to 27.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 20.9.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Llama 3.2 90B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 49.2 | 27.1 |
| Released | 2026-09-22 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 22 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-6 Sol: 59.6 (#11), Llama 3.2 90B: —
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1692 | — |
| LMArena Coding | 1453 | — |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 33.5 (#49), Llama 3.2 90B: 29.7 (#73)
Reasoning GPT-6 Sol leads
GPT-6 Sol: 49.3 (#34), Llama 3.2 90B: 20.9 (#207)
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| NYT Connections (extended) | 90.1% | — |
| EnigmaEval | — | 0.4% |
| EBR-Bench | 53.3% | — |
| LMArena Hard Prompts | 1420 | — |
| Epoch Capabilities Index | — | 125.5 |
Math GPT-6 Sol leads
GPT-6 Sol: 35.8 (#135), Llama 3.2 90B: 10.4 (#302)
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1404 | — |
| MATH Level 5 | — | 39.4% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 43.0 (#87), Llama 3.2 90B: 21.7 (#269)
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| Vectara Hallucination Rate | 6.5% | — |
| LMArena Expert | 1449 | — |
| MMLU | — | 80.3% |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#9), Llama 3.2 90B: 24.9 (#119)
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
| Furniture Assembly | 58.3% | — |
Multilingual Not comparable
GPT-6 Sol: 51.0 (#113), Llama 3.2 90B: —
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1389 | — |
| LMArena Chinese | 1416 | — |
| LMArena Russian | 1407 | — |
| LMArena Spanish | 1377 | — |
Instruction Following Not comparable
GPT-6 Sol: 74.4 (#97), Llama 3.2 90B: —
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1406 | — |
Long Context Not comparable
GPT-6 Sol: 43.2 (#100), Llama 3.2 90B: —
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1415 | — |
Writing & Preference Not comparable
GPT-6 Sol: 72.3 (#15), Llama 3.2 90B: —
| Benchmark | GPT-6 Sol | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1396 | — |
| LMArena Creative Writing | 1392 | — |
| EQ-Bench Creative Writing | 2125 | — |
| LMArena Multi-Turn | 1405 | — |
Frequently asked questions
Is GPT-6 Sol better than Llama 3.2 90B?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 27.1 on the Noometry Index.
How many benchmarks do GPT-6 Sol and Llama 3.2 90B share?
0 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and Llama 3.2 90B has 9.