GPT-5.5 vs GPT-6.1 Sol
GPT-6.1 Sol leads GPT-5.5 by 13.3 points on the Shogo Agent Index. GPT-5.5 wins 1 and GPT-6.1 Sol wins 18 of 20 shared benchmarks. GPT-6.1 Sol is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | GPT-5.5 | GPT-6.1 Sol |
|---|---|---|
| Agentic coding | 63 | 80 |
| Long-horizon autonomy | 67 | 78 |
| Knowledge-work agents | 46 | 54 |
| Computer use | 43 | 66 |
| Security & context learning | 55 | 62 |
Shared benchmarks
| Benchmark | GPT-5.5 | GPT-6.1 Sol |
|---|---|---|
| APEX-Agentsindex | 55.1% | 60.0% |
| Vending-Bench 2index | $7,524 | $12,861 |
| PostTrainBenchindex | 23.9% | 38.8% |
| ARC-AGI | 95.0% | 98.5% |
| ARC-AGI-2 | 85.0% | 94.2% |
| Chess Puzzles | 63.0% | 68.0% |
| CritPt | 27.1% | 31.7% |
| DTBench | 96.0% | 96.5% |
| FrontierCode | 43.0% | 50.2% |
| FrontierMath Tier 4 | 72.5% | 100.0% |
| FrontierMath Tiers 1-3 | 85.3% | 93.7% |
| GPQA Diamond | 94.0% | 95.4% |
| LMCA | 54.3% | 62.8% |
| MirrorCode | 23.3% | 61.1% |
| OTIS Mock AIME | 100.0% | 100.0% |
| ProofBench | 50.0% | 99.0% |
| SciCode | 56.1% | 55.8% |
| SimpleBench | 69.0% | 82.9% |
| SimpleQA Verified | 63.0% | 73.9% |
| WebDev Arena | 1510 | 1759 |
Specs and price
| GPT-5.5 | GPT-6.1 Sol | |
|---|---|---|
| Agent Index | 56.7 (#19) | 70 (#5) |
| Agent $/M | $2.55 | $0.84 |
| Input / output $/M | $5.00 / $30.00 | $2.00 / $10.00 |
| Context | 1.1M | 1.1M |
| Released | Apr 23, 2026 | Sep 29, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 6 |
Don’t pick one. Route.
Shogo can run GPT-5.5 and GPT-6.1 Sol side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo