AI Battle > Rankings > GPT-5.6 Luna (max)

GPT-5.6 Luna (max) — Placements in 58 Rankings (2026)

GPT-5.6 Luna (max), published by OpenAI, appears in 58 of the 129 datasets AI Battle tracks. Its strongest published placement is #1 of 11 in Cost per Task.

Last updated: . Every placement below comes from the named public dataset; AI Battle joins them by slug and changes nothing else.

All placements for GPT-5.6 Luna (max)

RankingRankValue
Cost per Task#1 of 110.18
Cost per Task#1 of 110.18
Pricing: Cache Hit, Input, and Output#3 of 200.20
Pricing: Cache Hit, Input, and Output#3 of 200.20
AA-Briefcase Cost per Task#3 of 200.05
AA-LCR v1.1: Cost per Task#3 of 200.02
𝜏³-Banking: Cost per Task#3 of 200.00
SciCode: Cost per Task#3 of 200.00
Cost per Intelligence Index Task#4 of 200.00
Cost per Intelligence Index Task#4 of 200.00
GDPval-AA v2: Cost per Task#4 of 200.00
MMMU-Pro: Total Cost to Run#4 of 190.59
Cost to Run Artificial Analysis Intelligence Index#5 of 2022.0
Cost to Run Artificial Analysis Intelligence Index#5 of 2022.0
Terminal-Bench v4.0: Cost per Task#5 of 200.00
Humanity's Last Exam: Cost per Task#6 of 200.00
𝜏³-Banking: Output Tokens per Task#6 of 202075
GDPval-AA v2: Output Tokens per Task#7 of 2018049
Speed#4 of 11116
Speed#4 of 11116
Context Window#8 of 201000000
Output Speed#8 of 20116
Output Speed#8 of 20116
AA-LCR v1.1: Time per Task#8 of 200.25
AA-Omniscience Index: Cost Breakdown#9 of 200.14
AA-Briefcase Output Tokens per Task#9 of 2042508
𝜏³-Banking: Time per Task#9 of 201.30
Time per Intelligence Index Task#10 of 206.10
Time per Intelligence Index Task#10 of 206.10
AA-LCR v1.1: Output Tokens per Task#10 of 2080.8
AA-LCR v1.1: Score#10 of 200.84
Output Tokens per Intelligence Index Task#11 of 2013136
Output Tokens per Intelligence Index Task#11 of 2013136
Terminal-Bench v4.0: Time per Task#13 of 2019.8
MMMU-Pro: Score#13 of 190.79
AA-Briefcase Elo#14 of 201339
GDPval-AA v2 Leaderboard#14 of 201489
AA-Briefcase Elo#14 of 201339
Artificial Analysis Intelligence Index by Open Weights / Proprietary#15 of 2037.5
Artificial Analysis Intelligence Index by Open Weights / Proprietary#15 of 2037.5
Artificial Analysis Intelligence Index#15 of 2037.5
Artificial Analysis Intelligence Index#15 of 2037.5
AA-Briefcase Tool Calls Breakdown, Avg per Task#15 of 2047.4
Humanity's Last Exam: Output Tokens per Task#16 of 20237
Humanity's Last Exam: Time per Task#16 of 203.60
Terminal-Bench v4.0: Output Tokens per Task#16 of 2041119
SciCode: Time per Task#16 of 201.07
SciCode: Output Tokens per Task#16 of 20419
MMMU-Pro: Token Usage#17 of 192959753
AA-Omniscience Accuracy#18 of 200.43
SciCode: Score#18 of 200.54
Intelligence#10 of 1137.5
Intelligence#10 of 1137.5
AA-Briefcase Elo#19 of 201339
Mean Turns per Task#19 of 2072.7
GDPval-AA v2 Leaderboard#19 of 201489
Humanity's Last Exam: Score#20 of 200.39
Terminal-Bench v4.0: Score#20 of 200.12

Price vs intelligence

GPT-5.6 Luna (max)intelligence index →input price / 1M → $4.00
Each dot is a model, joined by AI Battle from two public datasets — the intelligence index ranking and the published input pricing ranking. Every published value is shown as-is, no averaging. The dashed line is the value frontier: no model above or to the right of it offers a lower input price at its intelligence level.

How to read this profile

Each row is a separate measurement in a separate dataset — the position reflects the metric of that ranking, and a higher number is not "better" for every dataset (times and prices are costs). AI Battle deliberately does not average placements into a single score: datasets differ in coverage, so a total would hide more than it shows.

Raw data

Machine-readable profile: /data/models/gpt-5-6-luna.json.

Method

Placements, joins and this page are computed by AI Battle from public datasets — see the methodology for sources, limitations and corrections.