OpenAI

GPT-6 Luna (Max)

Released 2026-09-22 · Context 1050K · Data snapshot 2026-10-22

Overall score

57.5

Ranked #30
Benchmark coverage
81.8%
18 third-party benchmarks
Context window
1050K
tokens
Input price
$0.10
Cache read $0.01
Output price
$0.50
per million tokens
OpenRouter usage
#8
6.2T tokens/day

Prices converted at snapshot-day rate (USD/CNY 6.6761)

Dimension performance

Human preference63.2
Reasoning61.4
Knowledge57.7
Coding56.4
Office54.1
Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation

Benchmark details

Coding3 items
LiveBench 2.0 · Coding84.5
LiveBench 2.0 · Browser72
LiveBench 2.0 · Long Agentic48.1
Reasoning3 items
LiveBench 2.0 · Reasoning81.8
FrontierMath (Tiers 1-3)max78.9
AA Intelligence Indexxhigh34.6
Office9 items
LiveBench 2.0 · Design82.5
LiveBench 2.0 · Data Analysis73.4
LiveBench 2.0 · Research43.5
AA Strategy & Opsxhigh42.6
AA Economicsxhigh41.6
AA Finance & Accountingxhigh37.2
AA Legalxhigh37.2
AA Healthcare & Medicalxhigh35.9
AA Engineeringxhigh33.7
Knowledge2 items
GPQA Diamondmax90.5
SimpleQA Verifiedmax41.4
Human preference1 items
LMArena Human Blind Vote1440.9603

Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.

Score trend

2026-10-202026-10-22
View daily data
2026-10-2257.5
2026-10-2157.4
2026-10-2057.5
Scores and prices come from third-party public data (Artificial Analysis / LMArena / OpenRouter). 50 is the reference models’ average; every 15 points ≈ one standard deviation. Prices are converted at snapshot-day rates and provided for reference only. Return to LLM Leaderboard.