← Leaderboard

model profile

Excellent

GPT-5.6 Luna

OpenAI·gpt-5-6-luna

Rank · overall#36

Score69.7

Benchmark scores

4 benchmarks

Terminal-Bench 2.175.7%

Accuracy · Jul 11, 2026 · ± 1.3

Artificial Analysis51.2Intelligence Index

AA Coding Index71.4Coding Index

FrontierMath (Tier 4)61%

Accuracy · ± 7.7

Across harnesses

1 agents

Per-benchmark score · composite per harness. Tap a row to open that board.

Scraped and aggregated from public leaderboards · 2026-07-23