Ministral 8B (Dec '25)

Benchmark scores, pricing, speed and comparisons for Ministral 8B (Dec '25).

Ministral 8B (Dec '25) is an AI model from Mistral, released 2025-12-02. It scores 15.1 on the Intelligence Index, 9.8 on the Coding Index and 31.7 on the Math Index.

Ministral 8B (Dec '25) at a glance

Mistral released Ministral 8B (Dec '25) on December 2, 2025. It is marked as retired in the catalogue, so treat its numbers as a historical record.

Ministral 8B (Dec '25) scores 15.1 on the Intelligence Index, the overall score the AI Benchmark rankings sort models by. On the narrower indexes it scores 9.8 for coding and 31.7 for math. Of its 10 individual benchmark results, the highest is 64.2% 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 $0.15 per million input tokens and $0.15 per million output tokens, so a sample workload of 1 million input tokens and 200,000 output tokens costs about $0.18. It writes about 201 output tokens per second, so a 500-token answer takes roughly 2.5 seconds once output starts, after a wait of about 0.29 seconds for the first token.

Every pair of models in the catalogue has a head-to-head page. Pick Ministral 8B (Dec '25) and a rival on the model comparisons page to compare their scores, prices and speed side by side.

Key scores

Intelligence15.1Index score
Coding9.8Index score
Math31.7Index score
Speed200.8Tokens/sec
Blended Cost$0.15Per 1M tokens

How does Ministral 8B (Dec '25) score on each benchmark?

10 benchmark results for Ministral 8B (Dec '25).

MMLU Pro Knowledge
64.2%
GPQA Reasoning
47.1%
AIME 2025 Math
31.7%
LiveCodeBench Code
30.3%
IFBench Other
29.1%
TAU2 Other
26.6%
LCR Other
24.0%
SciCode Other
20.8%
HLE Other
4.3%
TerminalBench Hard Other
4.3%