Ministral 14B (Dec '25)

Benchmark scores, pricing, speed and comparisons for Ministral 14B (Dec '25).

Ministral 14B (Dec '25) is an AI model from Mistral, released 2025-12-02. It scores 16.3 on the Intelligence Index, 10.7 on the Coding Index and 30.0 on the Math Index.

Ministral 14B (Dec '25) at a glance

Mistral released Ministral 14B (Dec '25) on December 2, 2025. It is marked as retired in the catalogue, so treat its numbers as a historical record.

Ministral 14B (Dec '25) scores 16.3 on the Intelligence Index, the overall score the AI Benchmark rankings sort models by. On the narrower indexes it scores 10.7 for coding and 30.0 for math. Of its 10 individual benchmark results, the highest is 69.3% on MMLU Pro and the lowest is 4.3% on TerminalBench Hard. These scores come from independent third-party model evaluations, which Franklin AI syncs automatically each day.

It costs $0.20 per million input tokens and $0.20 per million output tokens, so a sample workload of 1 million input tokens and 200,000 output tokens costs about $0.24. It writes about 143 output tokens per second, so a 500-token answer takes roughly 3.5 seconds once output starts, after a wait of about 0.30 seconds for the first token.

Every pair of models in the catalogue has a head-to-head page. Pick Ministral 14B (Dec '25) and a rival on the model comparisons page to compare their scores, prices and speed side by side.

Key scores

Intelligence16.3Index score
Coding10.7Index score
Math30.0Index score
Speed142.8Tokens/sec
Blended Cost$0.20Per 1M tokens

How does Ministral 14B (Dec '25) score on each benchmark?

10 benchmark results for Ministral 14B (Dec '25).

MMLU Pro Knowledge
69.3%
GPQA Reasoning
57.2%
LiveCodeBench Code
35.1%
IFBench Other
32.0%
AIME 2025 Math
30.0%
TAU2 Other
27.2%
SciCode Other
23.6%
LCR Other
22.0%
HLE Other
4.6%
TerminalBench Hard Other
4.3%