Claude Opus 4.6 vs GPT-5.6 Luna
Claude Opus 4.6 leads GPT-5.6 Luna by 1.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.6 wins 10 and GPT-5.6 Luna wins 7 of 17 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Opus 4.6 | GPT-5.6 Luna |
|---|---|---|
| Agentic coding | 57 | 59 |
| Long-horizon autonomy | 67 | 61 |
| Knowledge-work agents | 41 | 39 |
| Computer use | 39 | 40 |
| Security & context learning | 57 | 51 |
Shared benchmarks
| Benchmark | Claude Opus 4.6 | GPT-5.6 Luna |
|---|---|---|
| APEX-Agentsindex | 46.3% | 43.0% |
| Vending-Bench 2index | $8,018 | $4,095 |
| ARC-AGI | 94.0% | 88.0% |
| ARC-AGI-2 | 69.2% | 59.5% |
| Chess Puzzles | 21.0% | 43.0% |
| DTBench | 91.2% | 89.1% |
| FrontierCode | 26.6% | 39.8% |
| FrontierMath Tier 4 | 26.8% | 61.0% |
| FrontierMath Tiers 1-3 | 66.0% | 82.1% |
| GPQA Diamond | 90.5% | 91.6% |
| LMCA | 55.8% | 48.5% |
| MirrorCode | 33.3% | 21.1% |
| OTIS Mock AIME | 94.4% | 98.3% |
| ProofBench | 50.0% | 60.0% |
| SimpleBench | 67.6% | 46.8% |
| SimpleQA Verified | 47.0% | 41.0% |
| WebDev Arena | 1556 | 1519 |
Specs and price
| Claude Opus 4.6 | GPT-5.6 Luna | |
|---|---|---|
| Agent Index | 53.2 (#31) | 51.4 (#34) |
| Agent $/M | $2.31 | $0.10 |
| Input / output $/M | $5.00 / $25.00 | $0.20 / $1.20 |
| Context | 1M | 1.1M |
| Released | Feb 5, 2026 | Jul 9, 2026 |
| Weights | Closed | Closed |
| API hosts | 5 | 5 |
Don’t pick one. Route.
Shogo can run Claude Opus 4.6 and GPT-5.6 Luna side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo