AI Battle > Rankings > DeepSeek V4.1 Flash (Reasoning, Max Effort)

DeepSeek V4.1 Flash (Reasoning, Max Effort) — Placements in 56 Rankings (2026)

DeepSeek V4.1 Flash (Reasoning, Max Effort), published by DeepSeek, appears in 56 of the 129 datasets AI Battle tracks. Its strongest published placement is #3 of 20 in End-to-End Response Time.

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

All placements for DeepSeek V4.1 Flash (Reasoning, Max Effort)

RankingRankValue
End-to-End Response Time#3 of 201.16
Latency: Time To First Answer Token#3 of 201.16
Cost per Task#2 of 110.27
Cost per Task#2 of 110.27
AA-Briefcase Tool Calls Breakdown, Avg per Task#4 of 2073.6
AA-Briefcase Cost per Task#4 of 200.10
GDPval-AA v2: Average Turns per Task#4 of 2072.1
Pricing: Cache Hit, Input, and Output#5 of 200.30
Output Speed#5 of 20222
Pricing: Cache Hit, Input, and Output#5 of 200.30
Output Speed#5 of 20222
Mean Turns per Task#5 of 20109
AA-LCR v1.1: Time per Task#5 of 200.19
AA-LCR v1.1: Cost per Task#5 of 200.03
GDPval-AA v2: Cost per Task#5 of 200.00
Speed#3 of 11222
Speed#3 of 11222
Cost per Intelligence Index Task#6 of 200.00
Cost to Run Artificial Analysis Intelligence Index#6 of 2040.4
Cost per Intelligence Index Task#6 of 200.00
Cost to Run Artificial Analysis Intelligence Index#6 of 2040.4
Terminal-Bench v4.0: Cost per Task#6 of 200.00
SciCode: Time per Task#6 of 200.59
SciCode: Cost per Task#6 of 200.00
GDPval-AA v2 Leaderboard#7 of 201632
Humanity's Last Exam: Cost per Task#7 of 200.00
MMMU-Pro: Total Cost to Run#7 of 190.25
Time per Intelligence Index Task#8 of 205.33
Time per Intelligence Index Task#8 of 205.33
Humanity's Last Exam: Time per Task#8 of 202.09
AA-Omniscience Index: Cost Breakdown#8 of 200.26
AA-LCR v1.1: Score#8 of 200.84
Model Size: Total and Active Parameters#6 of 1416.0
Time per Task#9 of 2015.0
Artificial Analysis Finance & Accounting Index#10 of 2045.1
AA-Briefcase Elo#12 of 201424
AA-Briefcase Elo#12 of 201424
Terminal-Bench v4.0: Time per Task#12 of 2017.2
GDPval-AA v2 Leaderboard#12 of 201632
Artificial Analysis Intelligence Index by Open Weights / Proprietary#14 of 2039.5
Artificial Analysis Intelligence Index by Open Weights / Proprietary#14 of 2039.5
Artificial Analysis Intelligence Index#14 of 2039.5
Artificial Analysis Intelligence Index#14 of 2039.5
Terminal-Bench v4.0: Score#15 of 200.27
MMMU-Pro: Score#15 of 190.77
AA-Omniscience Accuracy#16 of 200.46
Intelligence#9 of 1139.5
Intelligence#9 of 1139.5
Context Window#17 of 201000000
AA-Briefcase Rubric Pass Rate by File Type (Normalized)#17 of 200.72
AA-Briefcase Elo#17 of 201424
MMMU-Pro: Token Usage#18 of 19834480
SciCode: Score#19 of 200.52
AA-Omniscience Index#20 of 20-5.30
AA-Omniscience Index#20 of 20-5.30
SciCode: Output Tokens per Task#20 of 20356

Price vs intelligence

DeepSeek V4.1 Flash (Reaintelligence 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/deepseek-v4-1-flash.json.

Method

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