AI Battle > Rankings > Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B — Placements in 43 Rankings (2026)

Qwen3.8 2.4T A95B, published by Alibaba, appears in 43 of the 129 datasets AI Battle tracks. Its strongest published placement is #2 of 14 in Model Size: Total and Active Parameters.

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

All placements for Qwen3.8 2.4T A95B

RankingRankValue
Model Size: Total and Active Parameters#2 of 1495.0
AA-Briefcase Tool Calls Breakdown, Avg per Task#5 of 2080.4
𝜏³-Banking: Score#5 of 200.49
GDPval-AA v2: Average Turns per Task#6 of 2067.0
AA-LCR v1.1: Output Tokens per Task#7 of 20235
Mean Turns per Task#8 of 20101
GDPval-AA v2 Leaderboard#9 of 201628
AA-Omniscience Hallucination Rate#10 of 200.39
AA-Briefcase Elo#11 of 201439
AA-Briefcase Elo#11 of 201439
Artificial Analysis Finance & Accounting Index#12 of 2042.7
AA-Omniscience Index#13 of 204.32
Artificial Analysis Intelligence Index by Open Weights / Proprietary#13 of 2040.0
Artificial Analysis Intelligence Index by Open Weights / Proprietary#13 of 2040.0
Artificial Analysis Intelligence Index#13 of 2040.0
AA-Omniscience Index#13 of 204.32
Artificial Analysis Intelligence Index#13 of 2040.0
𝜏³-Banking: Output Tokens per Task#13 of 202794
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#14 of 200.76
GDPval-AA v2 Leaderboard#14 of 201628
Pricing: Cache Hit, Input, and Output#15 of 202.00
Pricing: Cache Hit, Input, and Output#15 of 202.00
Humanity's Last Exam: Cost per Task#15 of 200.00
Humanity's Last Exam: Score#16 of 200.42
AA-Briefcase Elo#16 of 201439
End-to-End Response Time#17 of 202.80
Latency: Time To First Answer Token#17 of 202.80
SciCode: Score#17 of 200.54
Cost to Run Artificial Analysis Intelligence Index#18 of 20176
Context Window#18 of 20983616
Cost to Run Artificial Analysis Intelligence Index#18 of 20176
AA-Omniscience Index: Score#18 of 204.32
AA-Briefcase Cost per Task#18 of 200.42
Output Tokens per Intelligence Index Task#19 of 2021878
Output Tokens per Intelligence Index Task#19 of 2021878
AA-LCR v1.1: Cost per Task#19 of 200.21
𝜏³-Banking: Cost per Task#19 of 200.00
Cost per Intelligence Index Task#20 of 200.02
Artificial Analysis Openness Index: Score#12 of 1227.8
Cost per Intelligence Index Task#20 of 200.02
Artificial Analysis Openness Index: Components#12 of 124.00
AA-LCR v1.1: Score#20 of 200.80
GDPval-AA v2: Cost per Task#20 of 200.00

Price vs intelligence

Qwen3.8 2.4T A95Bintelligence 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/qwen3-8-2-4t-a95b.json.

Method

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