LLMs TigerLive LLM benchmarks

GPT-5.6 Luna (max): benchmark scores, price and ranking

GPT-5.6 Luna (max) from OpenAI ranks #19 of 741 LLMs on the LLMs Tiger aggregate benchmark score (55.1), based on 18 benchmark results captured up to 2026-10-05.

Organisation
OpenAI
Type
Frontier model
Open weights
No
Released
2026-07-09 (source: epoch)
Cheapest API price
$0.200 in / $1.20 out per million tokens (via aihubmix, observed 2026-10-05T21:47Z)
Aggregate rank
#19 of 741 (score 55.1)

Relative to other models, GPT-5.6 Luna (max) is strongest on ALE-Bench (#6 of 78) and weakest on CursorBench (#11 of 13).

GPT-5.6 Luna (max) benchmark results

GPT-5.6 Luna (max) benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
ALE-Bench1,667#6 of 78Epoch AI Benchmarking Hub2026-10-05
OTIS Mock AIME98.3%#17 of 188Epoch AI Benchmarking Hub2026-10-05
GPQA Diamond91.6%#25 of 274Epoch AI Benchmarking Hub2026-10-05
Chess Puzzles40.0%#15 of 124Epoch AI Benchmarking Hub2026-10-05
LMCA48.5%#17 of 111Epoch AI Benchmarking Hub2026-10-05
CritPt20.6%#18 of 111Epoch AI Benchmarking Hub2026-10-05
BALROG45.6%#6 of 34Epoch AI Benchmarking Hub2026-10-05
FrontierMath T1-382.1%#14 of 69Epoch AI Benchmarking Hub2026-10-05
ProofBench60.0%#9 of 43Epoch AI Benchmarking Hub2026-10-05
DTBench88.8%#33 of 149Epoch AI Benchmarking Hub2026-10-05
SciCode53.6%#24 of 100Epoch AI Benchmarking Hub2026-10-05
FrontierMath T461.0%#15 of 52Epoch AI Benchmarking Hub2026-10-05
ARC-AGI-259.5%#32 of 89ARC Prize official leaderboard2026-10-05
DeepSWE67.2%#9 of 19Epoch AI Benchmarking Hub2026-10-05
Furniture Assembly42.5%#12 of 25Epoch AI Benchmarking Hub2026-10-05
SimpleQA Verified41.0%#35 of 66Epoch AI Benchmarking Hub2026-10-05
Mystery Games21.0%#31 of 57Epoch AI Benchmarking Hub2026-10-05
CursorBench35.9%#11 of 13Epoch AI Benchmarking Hub2026-10-05

GPT-5.6 Luna (max) is also listed at 7 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

Compare it on the live leaderboard → · How the aggregate score works