AI Battle > Rankings > Muse Spark 1.3 (max)

Muse Spark 1.3 (max) — Placements in 61 Rankings (2026)

Muse Spark 1.3 (max), published by Meta, appears in 61 of the 129 datasets AI Battle tracks. Its strongest published placement is #3 of 20 in AA-Briefcase Elo.

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

All placements for Muse Spark 1.3 (max)

RankingRankValue
AA-Briefcase Elo#3 of 201589
Output Speed#3 of 20233
GDPval-AA v2 Leaderboard#3 of 201703
AA-Briefcase Elo#3 of 201589
Output Speed#3 of 20233
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#3 of 200.95
GDPval-AA v2: Average Turns per Task#3 of 2074.5
𝜏³-Banking: Score#3 of 200.51
Speed#2 of 11233
Speed#2 of 11233
Artificial Analysis Intelligence Index by Open Weights / Proprietary#5 of 2048.2
Artificial Analysis Intelligence Index by Open Weights / Proprietary#5 of 2048.2
Artificial Analysis Intelligence Index#5 of 2048.2
Artificial Analysis Finance & Accounting Index#5 of 2049.9
Artificial Analysis Intelligence Index#5 of 2048.2
AA-Briefcase Elo#5 of 201589
GDPval-AA v2 Leaderboard#5 of 201703
𝜏³-Banking: Time per Task#5 of 201.00
AA-Omniscience Index#7 of 2025.0
Time per Intelligence Index Task#7 of 204.47
AA-Omniscience Index#7 of 2025.0
Time per Intelligence Index Task#7 of 204.47
AA-Omniscience Hallucination Rate#7 of 200.33
Intelligence#4 of 1148.2
Intelligence#4 of 1148.2
Time per Task#8 of 2010.6
SciCode: Time per Task#8 of 200.63
SciCode: Score#8 of 200.59
Cost per Task#5 of 111.60
Cost per Task#5 of 111.60
Humanity's Last Exam: Time per Task#10 of 202.27
AA-LCR v1.1: Time per Task#10 of 200.27
Context Window#11 of 201000000
Humanity's Last Exam: Cost per Task#11 of 200.00
Humanity's Last Exam: Score#11 of 200.49
Terminal-Bench v4.0: Time per Task#11 of 2015.5
Mean Turns per Task#11 of 2099.1
End-to-End Response Time#12 of 2022.2
AA-Omniscience Index: Score#12 of 2025.0
AA-LCR v1.1: Score#12 of 200.83
Pricing: Cache Hit, Input, and Output#13 of 201.25
Latency: Time To First Answer Token#13 of 2022.2
Pricing: Cache Hit, Input, and Output#13 of 201.25
Terminal-Bench v4.0: Score#13 of 200.33
AA-LCR v1.1: Cost per Task#13 of 200.12
SciCode: Cost per Task#13 of 200.00
Cost to Run Artificial Analysis Intelligence Index#14 of 20142
Cost to Run Artificial Analysis Intelligence Index#14 of 20142
AA-Briefcase Tool Calls Breakdown, Avg per Task#14 of 2042.5
Cost per Intelligence Index Task#15 of 200.02
Cost per Intelligence Index Task#15 of 200.02
AA-Briefcase Output Tokens per Task#15 of 2086653
Output Tokens per Intelligence Index Task#16 of 2026074
Output Tokens per Intelligence Index Task#16 of 2026074
GDPval-AA v2: Cost per Task#16 of 200.00
AA-Omniscience Accuracy#17 of 200.44
AA-Briefcase Cost per Task#17 of 200.37
𝜏³-Banking: Cost per Task#17 of 200.00
AA-Omniscience Index: Cost Breakdown#18 of 200.92
SciCode: Output Tokens per Task#18 of 20583
Terminal-Bench v4.0: Cost per Task#19 of 200.00

Price vs intelligence

Muse Spark 1.3 (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/muse-spark-1-3.json.

Method

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