AI Battle > Rankings > GPT-6 Astra (max)

GPT-6 Astra (max) — Placements in 51 Rankings (2026)

GPT-6 Astra (max), published by OpenAI, appears in 51 of the 129 datasets AI Battle tracks. Its strongest published placement is #1 of 19 in MMMU-Pro: Score.

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-6 Astra (max)

RankingRankValue
MMMU-Pro: Score#1 of 190.87
AA-Omniscience Index#2 of 2043.4
Artificial Analysis Intelligence Index by Open Weights / Proprietary#2 of 2052.8
Artificial Analysis Intelligence Index by Open Weights / Proprietary#2 of 2052.8
Artificial Analysis Intelligence Index#2 of 2052.8
Artificial Analysis Finance & Accounting Index#2 of 2055.5
AA-Omniscience Index#2 of 2043.4
Artificial Analysis Intelligence Index#2 of 2052.8
Terminal-Bench v4.0: Score#2 of 200.59
Humanity's Last Exam: Output Tokens per Task#3 of 20276
AA-LCR v1.1: Output Tokens per Task#3 of 2090.7
Intelligence#2 of 1152.8
Intelligence#2 of 1152.8
AA-Briefcase Elo#4 of 201562
AA-Briefcase Elo#4 of 201562
AA-Omniscience Index: Score#4 of 2043.4
MMMU-Pro: Token Usage#4 of 191000367
Output Tokens per Intelligence Index Task#5 of 2010514
Output Tokens per Intelligence Index Task#5 of 2010514
AA-Omniscience Accuracy#5 of 200.63
AA-AnalystAgent pass^5#3 of 110.51
Context Window#6 of 201000000
Humanity's Last Exam: Score#6 of 200.55
AA-Briefcase Elo#8 of 201562
AA-Briefcase Output Tokens per Task#8 of 2037019
Humanity's Last Exam: Time per Task#9 of 202.12
Terminal-Bench v4.0: Output Tokens per Task#9 of 2023336
GDPval-AA v2: Output Tokens per Task#9 of 2018050
SciCode: Output Tokens per Task#9 of 20400
GDPval-AA v2 Leaderboard#11 of 201580
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#11 of 200.73
Time per Task#12 of 2021.7
AA-LCR v1.1: Time per Task#12 of 200.31
Time per Intelligence Index Task#13 of 207.69
Time per Intelligence Index Task#13 of 207.69
SciCode: Score#13 of 200.56
AA-Omniscience Hallucination Rate#14 of 200.51
Speed#8 of 1158.9
Speed#8 of 1158.9
AA-Omniscience Index: Token Usage#15 of 20740990
Terminal-Bench v4.0: Time per Task#16 of 2021.4
GDPval-AA v2 Leaderboard#16 of 201580
Cost per Task#9 of 113.26
Cost per Task#9 of 113.26
𝜏³-Banking: Score#17 of 200.41
MMMU-Pro: Total Cost to Run#17 of 1910.0
AA-LCR v1.1: Score#18 of 200.81
SciCode: Time per Task#18 of 201.18
Output Speed#19 of 2058.9
Output Speed#19 of 2058.9
𝜏³-Banking: Output Tokens per Task#20 of 202189

Price vs intelligence

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-6-astra.json.

Method

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