GPT-5.6 Luna 2026-07-30 (Max): benchmark scores, price and ranking

GPT-5.6 Luna 2026-07-30 (Max) from OpenAI ranks #158 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.9), based on 1 benchmark results captured up to 2026-10-13.

Organisation: OpenAI
Type: Frontier model
Open weights: No
Released: 2026-07-30 (source: name)
Aggregate rank: #158 of 743 (score 50.9)

Across the 1 benchmark where at least ten models are scored, GPT-5.6 Luna 2026-07-30 (Max) is in the top 10% on 0 and in the top half on 1.

GPT-5.6 Luna 2026-07-30 (Max) benchmark results

GPT-5.6 Luna 2026-07-30 (Max) benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
ARC-AGI-2	59.6%	#32 of 87	ARC Prize official leaderboard	2026-10-13

About GPT-5.6 Luna 2026-07-30 (Max)

GPT-5.6 Luna 2026-07-30 (Max) is a frontier model from OpenAI. It was released on 2026-07-30, according to the model's own name. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where GPT-5.6 Luna 2026-07-30 (Max) stands

On our aggregate score, GPT-5.6 Luna 2026-07-30 (Max) is #158 of 743 ranked models, in the top quarter. Its score is 50.9; the scale is centred on 50, so it sits 0.9 points above the typical model. That beats 79% of the ranked field. Among the 88 ranked OpenAI models it is #20. The next one up is GPT-5 (high) at 51.1. The next one down is GPT-4 (0613) at 50.8.

GPT-5.6 Luna 2026-07-30 (Max), benchmark by benchmark

ARC-AGI-2 puts GPT-5.6 Luna 2026-07-30 (Max) at 59.6%, #32 of 87. That beats 63% of the models tested, but 35.4 points short of GPT-6 Astra (max) (95.0%). The results either side are Kimi K3 (max) (60.4%) and GPT-5.6 Luna (max) (59.5%). It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so GPT-5.6 Luna 2026-07-30 (Max) is 36.8 points above it. Source: ARC Prize official leaderboard, captured 2026-10-13.

Release history

The OpenAI model released before it was gpt-5.6-terra-xhigh (codex-harness) on 2026-07-09, which scores 47.3. The next one was GPT-6 Astra (max) on 2026-09-03, at 64.0.

Reading these numbers

The 1 score on this page comes from 1 source: ARC Prize official leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. The leaderboard also lists 5 other reasoning-effort settings of this model, which redirect here. This page shows the highest. With 1 results the aggregate rank can move a lot when one new score arrives.

GPT-5.6 Luna 2026-07-30 (Max) is also listed at 5 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

#155 claude-sonnet-4-20250514_59K (50.9)
#156 Dracarys2-72B-Instruct (50.9)
#157 gemini-1.5-pro-exp-0827 (50.9)
#159 LongCat-Flash-Thinking-2601 (50.9)
#160 MiniMax-M1-80k (50.9)
#161 Optimus Alpha (50.9)