Model comparison
GPT-6 Sol vs Llama 3.1-405B
GPT-6 Sol is the stronger model overall, scoring 61.8 to 30.7 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6 Sol and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Llama 3.1-405B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 61.8 | 30.7 |
| Released | 2026-09-22 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 45 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), Llama 3.1-405B: 33.1 (#262)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1447 | 1291 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
| WeirdML | — | 21.4% |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 37.2 (#36), Llama 3.1-405B: 21.0 (#140)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| APEX-Agents | 54.3% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Llama 3.1-405B: 16.8 (#300)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1418 | 1269 |
| DTBench | 97.3% | 61.4% |
| Epoch Capabilities Index | 162.72 | 128.75 |
| ARC-AGI-2 | 89.6% | — |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 30.9% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| LMCA | 59.1% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Llama 3.1-405B: 18.4 (#290)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 9.7% |
| LMArena Math | 1402 | 1281 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| ProofBench | 83% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Llama 3.1-405B: 30.4 (#227)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 94.3% | 50.9% |
| LMArena Expert | 1439 | 1243 |
| SimpleQA Verified | 60.7% | — |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| Vectara Hallucination Rate | 6.5% | — |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Llama 3.1-405B: —
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 50.5 (#118), Llama 3.1-405B: 40.7 (#214)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1385 | 1248 |
| LMArena Chinese | 1405 | 1242 |
| LMArena French | 1410 | 1279 |
| LMArena German | 1390 | 1252 |
| LMArena Japanese | 1385 | 1208 |
| LMArena Korean | 1341 | 1184 |
| LMArena Russian | 1401 | 1265 |
| LMArena Spanish | 1384 | 1260 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.5 (#94), Llama 3.1-405B: 65.9 (#214)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1412 | 1259 |
| IFEval | — | 81.1% |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.1 (#108), Llama 3.1-405B: 38.4 (#197)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1411 | 1266 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Llama 3.1-405B: 38.9 (#251)
| Benchmark | GPT-6 Sol | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1395 | 1284 |
| LMArena Creative Writing | 1378 | 1262 |
| EQ-Bench Creative Writing | 2125 | 870 |
| LMArena Multi-Turn | 1412 | 1297 |
| WildBench | — | 78.3% |
Frequently asked questions
Is GPT-6 Sol better than Llama 3.1-405B?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 30.7 on the Noometry Index.
Is GPT-6 Sol or Llama 3.1-405B better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 33.1 in the Noometry coding category.
How many benchmarks do GPT-6 Sol and Llama 3.1-405B share?
22 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Llama 3.1-405B has 42.