AI Battle > Rankings > Mistral Medium 3.5

Mistral Medium 3.5 — Placements in 41 Rankings (2026)

Mistral Medium 3.5, published by Mistral, appears in 41 of the 129 datasets AI Battle tracks. Its strongest published placement is #2 of 20 in GDPval-AA v2: Output Tokens 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 Mistral Medium 3.5

RankingRankValue
GDPval-AA v2: Output Tokens per Task#2 of 2017551
Output Tokens per Intelligence Index Task#3 of 2012066
Output Tokens per Intelligence Index Task#3 of 2012066
AA-Briefcase Output Tokens per Task#3 of 2032097
Time per Task#3 of 204.67
Terminal-Bench v4.0: Time per Task#4 of 207.15
Time per Intelligence Index Task#5 of 202.77
Latency: Time To First Answer Token#5 of 202.25
Time per Intelligence Index Task#5 of 202.77
End-to-End Response Time#6 of 202.25
AA-Briefcase Cost per Task#6 of 200.24
Cost per Intelligence Index Task#7 of 200.02
Output Speed#7 of 20147
Cost per Intelligence Index Task#7 of 200.02
Output Speed#7 of 20147
Terminal-Bench v4.0: Cost per Task#7 of 200.00
𝜏³-Banking: Time per Task#7 of 201.12
Terminal-Bench v4.0: Output Tokens per Task#8 of 2038059
GDPval-AA v2: Cost per Task#8 of 200.00
Cost to Run Artificial Analysis Intelligence Index#11 of 20132
Cost to Run Artificial Analysis Intelligence Index#11 of 20132
MMMU-Pro: Token Usage#11 of 19330058
Humanity's Last Exam: Time per Task#12 of 202.86
AA-Omniscience Index: Token Usage#13 of 20708722
MMMU-Pro: Total Cost to Run#13 of 190.50
AA-Omniscience Index: Cost Breakdown#14 of 201.06
𝜏³-Banking: Cost per Task#14 of 200.00
Model Size: Total and Active Parameters#11 of 14128
Humanity's Last Exam: Cost per Task#16 of 200.00
AA-LCR v1.1: Cost per Task#16 of 200.14
AA-AnalystAgent pass^5#9 of 110.13
Pricing: Cache Hit, Input, and Output#17 of 201.50
Pricing: Cache Hit, Input, and Output#17 of 201.50
AA-LCR v1.1: Time per Task#17 of 200.42
𝜏³-Banking: Output Tokens per Task#17 of 202300
SciCode: Time per Task#17 of 201.12
Artificial Analysis Openness Index: Score#11 of 1233.3
Artificial Analysis Openness Index: Components#11 of 125.00
Humanity's Last Exam: Output Tokens per Task#20 of 20331
MMMU-Pro: Score#19 of 190.65
SciCode: Cost per Task#20 of 200.00

Price vs intelligence

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/mistral-medium-3-5.json.

Method

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