# GPT-6 Sol vs o1-mini

> GPT-6 Sol is the stronger model overall, scoring 61.8 to 34.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-6-sol-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 8.8.
- The biggest single-benchmark swing is ARC-AGI-2: 89.6% for GPT-6 Sol and 0.8% for o1-mini.

## Snapshot

| | GPT-6 Sol | o1-mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 61.8 | 34.0 |
| Rank | 12 | 235 |
| Context | 1.05M | — |
| Input $/M | $2 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-6 Sol: 60.1 (#11)
- o1-mini: 35.5 (#224)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| LMArena Coding | 1447 | 1362 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| ALE-Bench | 2,462 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |

## Agentic & Tool Use

- GPT-6 Sol: 37.2 (#36)
- o1-mini: 24.6 (#118)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| APEX-Agents | 54.3% | — |
| Cybench | — | 10% |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |

## Reasoning

- GPT-6 Sol: 74.0 (#9)
- o1-mini: 8.8 (#346)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| ARC-AGI-2 | 89.6% | 0.8% |
| ARC-AGI-1 | 95.5% | 14% |
| LMArena Hard Prompts | 1418 | 1333 |
| Epoch Capabilities Index | 162.72 | 135.82 |
| SimpleBench | — | 18.1% |
| NYT Connections (extended) | 90.1% | — |
| CritPt | 30.9% | — |
| EBR-Bench | 53.3% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 59.1% | — |
| LiveBench | — | 57.8% |

## Math

- GPT-6 Sol: 87.2 (#7)
- o1-mini: 35.4 (#186)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 46.9% |
| LMArena Math | 1402 | 1358 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| ProofBench | 83% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- GPT-6 Sol: 64.8 (#15)
- o1-mini: 34.9 (#192)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| GPQA Diamond | 94.3% | 62.4% |
| LMArena Expert | 1439 | 1316 |
| SimpleQA Verified | 60.7% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 6.5% | — |

## Multimodal

- GPT-6 Sol: 47.6 (#10)
- o1-mini: —

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |

## Multilingual

- GPT-6 Sol: 50.5 (#118)
- o1-mini: 43.6 (#182)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| LMArena Non-English | 1385 | 1289 |
| LMArena Chinese | 1405 | 1314 |
| LMArena French | 1410 | 1293 |
| LMArena German | 1390 | 1278 |
| LMArena Japanese | 1385 | 1245 |
| LMArena Korean | 1341 | 1223 |
| LMArena Russian | 1401 | 1283 |
| LMArena Spanish | 1384 | 1303 |

## Instruction Following

- GPT-6 Sol: 74.5 (#94)
- o1-mini: 66.7 (#206)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1412 | 1304 |
| LiveBench Instruction Following | — | 65.4% |

## Long Context

- GPT-6 Sol: 43.1 (#108)
- o1-mini: 40.1 (#161)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| LMArena Longer Query | 1411 | 1320 |

## Writing & Preference

- GPT-6 Sol: 71.9 (#18)
- o1-mini: 48.4 (#202)

| Benchmark | GPT-6 Sol | o1-mini |
|---|---|---|
| LMArena Text | 1395 | 1317 |
| LMArena Creative Writing | 1378 | 1244 |
| LMArena Multi-Turn | 1412 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 2125 | — |
| LiveBench Language | — | 40.9% |

## FAQ

### Is GPT-6 Sol better than o1-mini?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 34.0 on the Noometry Index.

### Is GPT-6 Sol or o1-mini better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 35.5 in the Noometry coding category.

### How many benchmarks do GPT-6 Sol and o1-mini share?

22 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and o1-mini has 39.