Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
GPT-6.1 Sol vs GPT-6 Sol: which is smarter?
GPT-6.1 Sol has an SI-IQ of 148 and GPT-6 Sol has 140. The table compares them area by area using only independent benchmark results.
| Metric | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| SI-IQ | 148144–152 | 140137–144 |
| Reasoning | 150 | 139 |
| Math | 148 | 143 |
| Knowledge | 147 | 138 |
| Developer | OpenAI | OpenAI |
| Released | Sep 29, 2026 | Sep 22, 2026 |
| Access | API access | API access |
| Price in / out (USD per 1M tokens) | $2.00 / $10 | $2.00 / $10 |
| Benchmarks used | 8 | 8 |
GPT-6.1 SolGPT-6 Sol
Benchmarks every compared model was tested on
Raw scores as published by the evaluators.
| Benchmark | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| Chess Puzzles | 68.0% | 56.0% |
| FrontierMath Tier 4 | 100.0% | 90.0% |
| FrontierMath Tiers 1–3 | 93.7% | 89.8% |
| Furniture Assembly | 80.0% | 58.3% |
| GPQA Diamond | 95.4% | 94.3% |
| GPQA Diamond (OpenRouter run) | 94.4% | 92.1% |
| Mystery Game Puzzles | 80.0% | 56.0% |
| OTIS Mock AIME 2024–2025 | 100.0% | 100.0% |
| SimpleQA Verified | 73.9% | 60.7% |
| τ²-bench Airline (OpenRouter run) | 68.2% | 70.2% |
On SI-IQ, GPT-6.1 Sol is ahead by 8 points, and the 90% intervals do not overlap.
Data sources: Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..