modelgrep
M

Mistral: Ministral 3 14B 2512

mistralai/ministral-14b-2512

138th smartest of 178ToolsJSONVision
Use via OpenRouter ↗
Intelligence
16.0
138th of 178
Design Elo
1126
Website
Speed
tokens/sec
Latency
first token
Input price
$0.200
96th cheapest
Context
262K

How it compares

Smarter than22%
of all ranked models
Cheaper than68%
of all ranked models

Overview

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

Benchmarks

independent · via OpenRouter
Artificial Analysis22th percentile
Intelligence Index
16.0
Coding Index
10.9
Agentic Index
17.4
GPQA Diamond
57%
Humanity's Last Exam
5%
SciCode
24%
Tau²-Bench (agentic)
27%
Design Arena · Elo1,017 tournaments
Website
1126
codecategories
1117
Game Dev
1107
3D
1071

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Mistral$0.200$0.20098.9%
NextBitfp8$0.350$0.35096.9%

Specifications

Context window262K
Max output
Knowledge cutoff
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price$0.020/M
ModeratedNo

Ministral 3 14B 2512 FAQ

How much does Ministral 3 14B 2512 cost?

Ministral 3 14B 2512 costs $0.200 per million input tokens and $0.200 per million output tokens via OpenRouter, making it 96th cheapest of 298 paid models.

How smart is Ministral 3 14B 2512?

Ministral 3 14B 2512 scores 16.0 on the Artificial Analysis Intelligence Index, ranking 138th of 178 benchmarked models, with a GPQA Diamond score of 57%.

What is Ministral 3 14B 2512's context window?

Ministral 3 14B 2512 supports a 262K-token context window. It accepts text, image input.

Compare head-to-head