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

GPT-5.6 Sol (max) — Placements in 56 Rankings (2026)

GPT-5.6 Sol (max), published by OpenAI, appears in 56 of the 129 datasets AI Battle tracks. Its strongest published placement is #3 of 20 in SciCode: Output Tokens 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 Sol (max)

RankingRankValue
SciCode: Output Tokens per Task#3 of 20381
𝜏³-Banking: Output Tokens per Task#4 of 202405
AA-LCR v1.1: Output Tokens per Task#5 of 2074.9
Artificial Analysis Intelligence Index by Open Weights / Proprietary#6 of 2047.1
Artificial Analysis Intelligence Index by Open Weights / Proprietary#6 of 2047.1
Artificial Analysis Intelligence Index#6 of 2047.1
Artificial Analysis Intelligence Index#6 of 2047.1
AA-Briefcase Output Tokens per Task#6 of 2034731
AA-LCR v1.1: Score#6 of 200.84
MMMU-Pro: Token Usage#6 of 19999093
Output Tokens per Intelligence Index Task#7 of 2012029
Artificial Analysis Finance & Accounting Index#7 of 2049.2
Output Tokens per Intelligence Index Task#7 of 2012029
Humanity's Last Exam: Output Tokens per Task#7 of 20218
AA-Omniscience Index#8 of 2022.0
AA-Omniscience Index#8 of 2022.0
AA-Briefcase Elo#9 of 201475
AA-Briefcase Elo#9 of 201475
AA-AnalystAgent pass^5#5 of 110.47
MMMU-Pro: Score#9 of 190.83
GDPval-AA v2 Leaderboard#10 of 201624
Humanity's Last Exam: Score#10 of 200.49
Terminal-Bench v4.0: Output Tokens per Task#10 of 2037485
AA-Omniscience Accuracy#10 of 200.59
GDPval-AA v2: Output Tokens per Task#10 of 2022677
Terminal-Bench v4.0: Score#11 of 200.40
Time per Task#11 of 2020.3
SciCode: Score#11 of 200.57
AA-Omniscience Index: Score#13 of 2022.0
SciCode: Time per Task#13 of 200.95
Time per Intelligence Index Task#14 of 207.96
Time per Intelligence Index Task#14 of 207.96
AA-Briefcase Elo#14 of 201475
AA-LCR v1.1: Time per Task#14 of 200.33
GDPval-AA v2: Average Turns per Task#14 of 2045.2
Terminal-Bench v4.0: Time per Task#15 of 2020.9
GDPval-AA v2 Leaderboard#15 of 201624
𝜏³-Banking: Score#15 of 200.44
MMMU-Pro: Total Cost to Run#15 of 194.00
Context Window#16 of 201000000
AA-Briefcase Cost per Task#16 of 200.69
Cost per Intelligence Index Task#17 of 200.09
Output Speed#17 of 2061.4
Cost per Intelligence Index Task#17 of 200.09
Output Speed#17 of 2061.4
Humanity's Last Exam: Time per Task#17 of 203.62
Cost to Run Artificial Analysis Intelligence Index#19 of 20348
Cost to Run Artificial Analysis Intelligence Index#19 of 20348
𝜏³-Banking: Time per Task#19 of 202.33
SciCode: Cost per Task#19 of 200.01
End-to-End Response Time#20 of 20112
Pricing: Cache Hit, Input, and Output#20 of 204.00
Latency: Time To First Answer Token#20 of 20112
Pricing: Cache Hit, Input, and Output#20 of 204.00
AA-Briefcase Tool Calls Breakdown, Avg per Task#20 of 2040.6
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#20 of 200.55

Price vs intelligence

GPT-5.6 Sol (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-sol.json.

Method

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