GPT-6.1 Sol vs GPT-6 Sol
| Spec | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| Respan Index | 69.8 (#12) | 63.1 (#18) |
| Blended price per 1M | $4 | $4 |
| Context window | 1.1M | 1.1M |
| Input / output per 1M | $2 / $10 | $2 / $10 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-09-29 | 2026-09-22 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| Coding | 52.8 GPT-6.1 Sol | 44.8 GPT-6 Sol |
| Agents | 73.0 GPT-6.1 Sol | 71.0 GPT-6 Sol |
| Reasoning | 87.4 GPT-6.1 Sol | 77.3 GPT-6 Sol |
| Knowledge & language | 74.4 GPT-6.1 Sol | 60.6 GPT-6 Sol |
| Human preference | 60.3 GPT-6.1 Sol | 58.3 GPT-6 Sol |
Benchmarks both report
GPT-6.1 Sol leads on 23 of the 26 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| LMArena Agent (LMArena) | 0.1131 | 0.0647 |
| LMArena Elo | 1483 | 1458 |
| LMArena WebDev (LMArena) | 1744 | 1674 |
| Vending-Bench 2 (Andon Labs) | 12860.61 | 14427.85 |
| LMArena Vision (LMArena) | 1293 | 1258 |
| MirrorCode (Epoch AI) | 61.1% | 48.9% |
| Chess Puzzles (Epoch AI) | 68% | 56% |
| APEX-Agents (Mercor) | 60% | 54.3% |
| EBR-bench (Epoch AI) | 54.3% | 53.3% |
| FrontierMath Tier 4 v2 (Epoch AI) | 100% | 90% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 93.7% | 89.8% |
| Furniture Assembly (Epoch AI) | 80% | 58.3% |
| GPQA Diamond | 95.4% | 94.3% |
| LiveBench Agentic Coding (LiveBench) | 56.8% | 52.9% |
| LiveBench Coding (LiveBench) | 80.7% | 81.8% |
| LiveBench Data Analysis (LiveBench) | 82.7% | 81.2% |
| LiveBench Instruction Following (LiveBench) | 74.2% | 68.6% |
| LiveBench Language (LiveBench) | 90.1% | 85.3% |
| LiveBench Mathematics (LiveBench) | 96.8% | 96.4% |
| LiveBench Reasoning (LiveBench) | 92.6% | 88.7% |
| Mystery Game Puzzles (Epoch AI) | 80% | 56% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 100% |
| SAGE (Vals AI) | 46.5% | 44.8% |
| SimpleQA Verified | 73.9% | 60.7% |
| Terminal-Bench 4.0 (Vals AI) | 55.1% | 44.4% |
| SimpleBench (SimpleBench) | 82.9% | 73.1% |
FAQ
Is GPT-6.1 Sol better than GPT-6 Sol?
GPT-6.1 Sol scores 69.8 on the Respan Index (#12), ahead of GPT-6 Sol at 63.1 (#18). GPT-6.1 Sol leads on 23 of the 26 benchmarks both report.
Which is cheaper, GPT-6.1 Sol or GPT-6 Sol?
GPT-6.1 Sol lists at $2 input and $10 output per 1M tokens; GPT-6 Sol at $2 and $10. Both cost about the same per token at list price.
Which has the larger context window?
Both accept 1.1M tokens of context.