AI Battle > Rankings > Kimi K3 (max)

Kimi K3 (max) — Placements in 60 Rankings (2026)

Kimi K3 (max), published by Kimi, appears in 60 of the 129 datasets AI Battle tracks. Its strongest published placement is #1 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 Kimi K3 (max)

RankingRankValue
Context Window#1 of 201048576
AA-LCR v1.1: Score#1 of 200.89
Model Size: Total and Active Parameters#1 of 14104
SciCode: Output Tokens per Task#4 of 20466
SciCode: Score#6 of 200.59
AA-Briefcase Elo#8 of 201488
AA-Briefcase Elo#8 of 201488
AA-LCR v1.1: Output Tokens per Task#8 of 20110
Artificial Analysis Openness Index: Score#5 of 1238.9
AA-Omniscience Index#9 of 2019.7
Artificial Analysis Intelligence Index by Open Weights / Proprietary#9 of 2043.8
Artificial Analysis Intelligence Index by Open Weights / Proprietary#9 of 2043.8
Artificial Analysis Intelligence Index#9 of 2043.8
Artificial Analysis Finance & Accounting Index#9 of 2046.9
AA-Omniscience Index#9 of 2019.7
Artificial Analysis Intelligence Index#9 of 2043.8
AA-Briefcase Tool Calls Breakdown, Avg per Task#9 of 2054.4
MMMU-Pro: Score#11 of 190.81
GDPval-AA v2 Leaderboard#12 of 201552
𝜏³-Banking: Score#12 of 200.46
𝜏³-Banking: Output Tokens per Task#12 of 203497
Cost per Task#7 of 112.00
Intelligence#7 of 1143.8
AA-AnalystAgent pass^5#7 of 110.39
Cost per Task#7 of 112.00
Intelligence#7 of 1143.8
Output Tokens per Intelligence Index Task#13 of 2016002
Output Tokens per Intelligence Index Task#13 of 2016002
Humanity's Last Exam: Score#13 of 200.47
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#13 of 200.77
AA-Briefcase Elo#13 of 201488
Artificial Analysis Openness Index: Components#8 of 124.00
Terminal-Bench v4.0: Output Tokens per Task#14 of 2030360
AA-Omniscience Index: Score#14 of 2019.7
AA-Omniscience Accuracy#14 of 200.48
GDPval-AA v2: Output Tokens per Task#14 of 2025870
Terminal-Bench v4.0: Cost per Task#15 of 200.00
AA-Omniscience Hallucination Rate#15 of 200.53
Mean Turns per Task#15 of 2082.6
MMMU-Pro: Token Usage#15 of 191210646
SciCode: Cost per Task#16 of 200.01
GDPval-AA v2 Leaderboard#17 of 201552
GDPval-AA v2: Cost per Task#17 of 200.00
End-to-End Response Time#18 of 204.46
Cost per Intelligence Index Task#18 of 200.07
Latency: Time To First Answer Token#18 of 204.46
Cost per Intelligence Index Task#18 of 200.07
Humanity's Last Exam: Output Tokens per Task#18 of 20240
AA-Briefcase Output Tokens per Task#18 of 2063408
Pricing: Cache Hit, Input, and Output#19 of 203.00
Pricing: Cache Hit, Input, and Output#19 of 203.00
Terminal-Bench v4.0: Score#19 of 200.13
GDPval-AA v2: Average Turns per Task#19 of 2037.5
Cost to Run Artificial Analysis Intelligence Index#20 of 20322
Speed#11 of 1135.1
Cost to Run Artificial Analysis Intelligence Index#20 of 20322
Speed#11 of 1135.1
MMMU-Pro: Total Cost to Run#19 of 193.63
AA-LCR v1.1: Cost per Task#20 of 200.29
SciCode: Time per Task#20 of 201.53

Price vs intelligence

Kimi K3 (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/kimi-k3.json.

Method

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