GPT 5.6 Luna
OpenAI closed 2026-07-09
Legacy
Killed
GPT 5.6 Luna is killed. The executioner, Claude Haiku 5.5, costs $0.20 and scores 43.4: no more expensive, no weaker. Choosing GPT 5.6 Luna means paying more for nothing.
- Score
- 37.3
- Artificial Analysis Intelligence Index
- Best rank
- #30
- Terminal-Bench 4.0
- Price
- $0.45
- Blended Price, USD per 1M tokens (3:1 input:output)
- Best effort
- max
- Artificial Analysis LLM Leaderboard
No longer listed as current by its source, so this page shows only the verdict and its scores.
Scores on each board Each rank is the board’s own: the rank it publishes, or the model’s place in the board’s own order where it publishes none. The bar shows how much of that board the model ranks ahead of. Scores from different boards cannot be compared.
- Artificial Analysis LLM LeaderboardArtificial Analysis Intelligence Index37.3No. 37 of 375
- Arena — AgentOverall-0.015No. 36 of 52
- Artificial Analysis Coding AgentsArtificial Analysis Coding Agent Index0.432No. 19 of 24
- Epoch AI Benchmarking HubFrontierMath Tiers 1–382.1%No. 14 of 82
- HarnessTax — SWE-bench LiteSWE-bench Lite55.6%No. 7 of 7
- HarnessTax — Terminal-Bench 2.0Terminal-Bench 2.076.7%No. 2 of 7
- Terminal-Bench 4.0Terminal-Bench 4.017.3%No. 30 of 35
- Arena — CodeOverall1519No. 51 of 142
- Arena — TextOverall (style control)1452No. 74 of 414
- Arena — VisionOverall (style control)1258No. 48 of 165
Compare with the executioner, Claude Haiku 5.5 → See the current SOTA models →
Details
- Family
- GPT → GPT 5.6
- Blended Price, USD per 1M tokens (3:1 input:output)
- $0.45
- Sources
- 10 boards ·21 scores ·12 settings
- Also written as
-
GPT-5.6 Lunagpt-5-6-lunaGPT 5.6 Lunagpt-5.6-luna