AI Battle > Rankings > GLM-5.3 (max)

GLM-5.3 (max) — Placements in 57 Rankings (2026)

GLM-5.3 (max), published by Z AI, appears in 57 of the 129 datasets AI Battle tracks. Its strongest published placement is #3 of 20 in AA-Briefcase Tool Calls Breakdown, Avg 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 GLM-5.3 (max)

RankingRankValue
AA-Briefcase Tool Calls Breakdown, Avg per Task#3 of 2080.1
GDPval-AA v2 Leaderboard#4 of 201655
AA-Omniscience Hallucination Rate#4 of 200.30
Mean Turns per Task#4 of 20110
𝜏³-Banking: Score#4 of 200.50
GDPval-AA v2: Average Turns per Task#5 of 2070.0
𝜏³-Banking: Output Tokens per Task#5 of 202546
AA-Briefcase Elo#7 of 201511
Artificial Analysis Intelligence Index by Open Weights / Proprietary#7 of 2044.9
Artificial Analysis Intelligence Index by Open Weights / Proprietary#7 of 2044.9
Artificial Analysis Intelligence Index#7 of 2044.9
AA-Briefcase Elo#7 of 201511
Artificial Analysis Intelligence Index#7 of 2044.9
SciCode: Score#7 of 200.59
Model Size: Total and Active Parameters#5 of 1440.0
GDPval-AA v2 Leaderboard#8 of 201655
Intelligence#5 of 1144.9
Intelligence#5 of 1144.9
AA-Omniscience Index#10 of 2014.3
AA-Omniscience Index#10 of 2014.3
Terminal-Bench v4.0: Score#10 of 200.42
Speed#6 of 1173.0
Speed#6 of 1173.0
Artificial Analysis Finance & Accounting Index#11 of 2044.7
AA-Omniscience Index: Cost Breakdown#11 of 201.07
𝜏³-Banking: Cost per Task#11 of 200.00
Latency: Time To First Answer Token#12 of 203.08
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#12 of 200.78
AA-Briefcase Elo#12 of 201511
End-to-End Response Time#13 of 203.08
Pricing: Cache Hit, Input, and Output#14 of 201.40
Pricing: Cache Hit, Input, and Output#14 of 201.40
𝜏³-Banking: Time per Task#14 of 201.68
Cost per Task#8 of 112.01
Cost per Task#8 of 112.01
Context Window#15 of 201000000
Output Speed#15 of 2073.0
Artificial Analysis Openness Index: Score#9 of 1233.3
Output Speed#15 of 2073.0
AA-Omniscience Index: Score#15 of 2014.3
AA-LCR v1.1: Cost per Task#15 of 200.14
Artificial Analysis Openness Index: Components#10 of 125.00
Cost to Run Artificial Analysis Intelligence Index#17 of 20128
Cost to Run Artificial Analysis Intelligence Index#17 of 20128
Humanity's Last Exam: Score#17 of 200.42
AA-Omniscience Index: Token Usage#17 of 20761402
GDPval-AA v2: Cost per Task#18 of 200.00
Cost per Intelligence Index Task#19 of 200.01
Cost per Intelligence Index Task#19 of 200.01
Humanity's Last Exam: Cost per Task#19 of 200.00
Time per Task#19 of 2036.8
Time per Intelligence Index Task#20 of 2013.9
Time per Intelligence Index Task#20 of 2013.9
AA-Omniscience Accuracy#20 of 200.34
AA-Briefcase Cost per Task#20 of 200.35
AA-Briefcase Output Tokens per Task#20 of 2079938
AA-LCR v1.1: Output Tokens per Task#20 of 20102

Price vs intelligence

GLM-5.3 (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/glm-5-3.json.

Method

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