Model comparison
GPT-6 Sol vs Grok 4.1
GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GPT-6 Sol scores higher in 7 categories and Grok 4.1 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 38.9.
Side by side
| GPT-6 Sol | Grok 4.1 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 61.8 | 41.5 |
| Released | 2026-09-22 | 2025-11-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 45 | 19 |
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), Grok 4.1: 33.7 (#253)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena WebDev | 1688 | 1214 |
| LMArena Coding | 1447 | 1445 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| SciCode | 57.6% | — |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 37.2 (#36), Grok 4.1: 34.1 (#49)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| APEX-Agents | 54.3% | — |
| Cybench | — | 39% |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Grok 4.1: 29.5 (#91)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Hard Prompts | 1418 | 1435 |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 30.9% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
| Epoch Capabilities Index | 162.72 | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Grok 4.1: 38.9 (#120)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Math | 1402 | 1422 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 83% | — |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Grok 4.1: 39.5 (#133)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Expert | 1439 | 1417 |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Grok 4.1: —
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual Grok 4.1 leads
GPT-6 Sol: 50.5 (#118), Grok 4.1: 53.4 (#68)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Non-English | 1385 | 1425 |
| LMArena Chinese | 1405 | 1465 |
| LMArena French | 1410 | 1448 |
| LMArena German | 1390 | 1446 |
| LMArena Japanese | 1385 | 1397 |
| LMArena Korean | 1341 | 1407 |
| LMArena Russian | 1401 | 1434 |
| LMArena Spanish | 1384 | 1438 |
Instruction Following Too close to call
GPT-6 Sol: 74.5 (#94), Grok 4.1: 73.8 (#111)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Instruction Following | 1412 | 1400 |
Long Context Too close to call
GPT-6 Sol: 43.1 (#108), Grok 4.1: 43.2 (#100)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Longer Query | 1411 | 1416 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Grok 4.1: 62.4 (#75)
| Benchmark | GPT-6 Sol | Grok 4.1 |
|---|---|---|
| LMArena Text | 1395 | 1437 |
| LMArena Creative Writing | 1378 | 1411 |
| LMArena Multi-Turn | 1412 | 1437 |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than Grok 4.1?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.5 on the Noometry Index.
Is GPT-6 Sol or Grok 4.1 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 33.7 in the Noometry coding category.
How many benchmarks do GPT-6 Sol and Grok 4.1 share?
18 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Grok 4.1 has 19.