Claude Opus 4.6 vs GPT-6 Sol
GPT-6 Sol leads Claude Opus 4.6 by 10.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.6 wins 0 and GPT-6 Sol wins 17 of 17 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Opus 4.6 | GPT-6 Sol |
|---|---|---|
| Agentic coding | 57 | 72 |
| Long-horizon autonomy | 67 | 76 |
| Knowledge-work agents | 41 | 48 |
| Computer use | 39 | 54 |
| Security & context learning | 57 | 59 |
Shared benchmarks
| Benchmark | Claude Opus 4.6 | GPT-6 Sol |
|---|---|---|
| APEX-Agentsindex | 46.3% | 54.3% |
| Vending-Bench 2index | $8,018 | $14,428 |
| ARC-AGI | 94.0% | 95.5% |
| ARC-AGI-2 | 69.2% | 89.6% |
| Chess Puzzles | 21.0% | 56.0% |
| DTBench | 91.2% | 97.3% |
| FrontierCode | 26.6% | 49.3% |
| FrontierMath Tier 4 | 26.8% | 90.0% |
| FrontierMath Tiers 1-3 | 66.0% | 89.8% |
| GPQA Diamond | 90.5% | 94.3% |
| LMCA | 55.8% | 59.1% |
| MirrorCode | 33.3% | 48.9% |
| OTIS Mock AIME | 94.4% | 100.0% |
| ProofBench | 50.0% | 83.0% |
| SimpleBench | 67.6% | 73.1% |
| SimpleQA Verified | 47.0% | 60.7% |
| WebDev Arena | 1556 | 1689 |
Specs and price
| Claude Opus 4.6 | GPT-6 Sol | |
|---|---|---|
| Agent Index | 53.2 (#31) | 63.6 (#13) |
| Agent $/M | $2.31 | $0.92 |
| Input / output $/M | $5.00 / $25.00 | $2.00 / $10.00 |
| Context | 1M | 1.1M |
| Released | Feb 5, 2026 | Sep 22, 2026 |
| Weights | Closed | Closed |
| API hosts | 5 | 5 |
Don’t pick one. Route.
Shogo can run Claude Opus 4.6 and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo