AI Battle > Rankings > Inkling (xhigh)

Inkling (xhigh) — Placements in 52 Rankings (2026)

Inkling (xhigh), published by Thinking Machines, appears in 52 of the 129 datasets AI Battle tracks. Its strongest published placement is #3 of 20 in Context Window.

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

All placements for Inkling (xhigh)

RankingRankValue
Context Window#3 of 201000000
𝜏³-Banking: Output Tokens per Task#3 of 202278
AA-Briefcase Output Tokens per Task#5 of 2040704
GDPval-AA v2: Output Tokens per Task#5 of 2019971
Model Size: Total and Active Parameters#4 of 1441.0
Time per Task#6 of 2010.4
Output Tokens per Intelligence Index Task#8 of 2011257
Output Tokens per Intelligence Index Task#8 of 2011257
Terminal-Bench v4.0: Cost per Task#8 of 200.00
Artificial Analysis Openness Index: Components#5 of 126.00
Cost to Run Artificial Analysis Intelligence Index#9 of 2052.1
Time per Intelligence Index Task#9 of 206.10
Cost to Run Artificial Analysis Intelligence Index#9 of 2052.1
Time per Intelligence Index Task#9 of 206.10
Cost per Intelligence Index Task#10 of 200.01
Cost per Intelligence Index Task#10 of 200.01
Terminal-Bench v4.0: Time per Task#10 of 2015.4
GDPval-AA v2: Cost per Task#10 of 200.00
𝜏³-Banking: Time per Task#10 of 201.50
End-to-End Response Time#11 of 202.89
Pricing: Cache Hit, Input, and Output#11 of 201.00
Latency: Time To First Answer Token#11 of 202.89
Pricing: Cache Hit, Input, and Output#11 of 201.00
Terminal-Bench v4.0: Output Tokens per Task#11 of 2025951
AA-Briefcase Cost per Task#11 of 200.16
Artificial Analysis Openness Index: Score#7 of 1238.9
AA-LCR v1.1: Cost per Task#12 of 200.09
MMMU-Pro: Total Cost to Run#12 of 191.76
𝜏³-Banking: Cost per Task#13 of 200.00
AA-Omniscience Index#14 of 202.00
Output Speed#14 of 2089.2
AA-Omniscience Index#14 of 202.00
Output Speed#14 of 2089.2
Humanity's Last Exam: Cost per Task#14 of 200.00
AA-AnalystAgent pass^5#8 of 110.24
SciCode: Cost per Task#15 of 200.00
AA-LCR v1.1: Output Tokens per Task#16 of 20150
GDPval-AA v2: Average Turns per Task#16 of 2043.1
AA-Omniscience Index: Cost Breakdown#17 of 200.78
Mean Turns per Task#17 of 2081.5
AA-LCR v1.1: Time per Task#18 of 200.42
MMMU-Pro: Score#18 of 190.73
Artificial Analysis Finance & Accounting Index#19 of 2030.3
AA-Omniscience Hallucination Rate#19 of 200.68
AA-Omniscience Index: Score#19 of 202.00
AA-Omniscience Accuracy#19 of 200.42
Artificial Analysis Intelligence Index by Open Weights / Proprietary#20 of 2025.5
GDPval-AA v2 Leaderboard#20 of 201165
Artificial Analysis Intelligence Index by Open Weights / Proprietary#20 of 2025.5
Artificial Analysis Intelligence Index#20 of 2025.5
Artificial Analysis Intelligence Index#20 of 2025.5
MMMU-Pro: Token Usage#19 of 191764121

Price vs intelligence

Inkling (xhigh)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/inkling.json.

Method

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