Mistral AIOpen weightsAuto-detected

Ministral 3 14B

Name: Ministral 3 14B benchmark results
Creator: BenchLeader

Best configuration ranks #505 of 610 on the BenchLeader Index at 40.5 ±1.6. Released 2 Dec 2025.

Blended price: $0.200/M; $0.200 in · $0.200 out
Output speed: 88 tok/s
First answer: 0.86 s; first token 0.86 s
Context: 262k

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index41
Agents & tools38
Knowledge33
Instruction following36
Multimodal34
Long context38
Composite37

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	default	Source
GPQA Diamond (AA)not in index	57.2%#374	Artificial Analysis
Humanity's Last Exam (AA)not in index	4.6%#406	Artificial Analysis

Coding

Benchmark	default	Source
SciCode (AA)not in index	23.8%#155	Artificial Analysis

Agents & tools

Benchmark	default	Source
Terminal-Bench Hard	4.5%#270	Artificial Analysis
τ²-Bench Telecom (AA)not in index	27.2%#269	Artificial Analysis

Knowledge

Benchmark	default	Source
AA-Omniscience	-66.4#426	Artificial Analysis

Instruction following

Benchmark	default	Source
IFBench	32.0%#328	Artificial Analysis

Multimodal

Benchmark	default	Source
MMMU-Pro	49.8%#207	Artificial Analysis

Long context

Benchmark	default	Source
AA-LCR	26.3%#335	Artificial Analysis

Composite

Benchmark	default	Source
AA Intelligence Index	6.0#458	Artificial Analysis

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

Workload	Tokens in / out	Cost	With caching	Time
Chat reply	400 / 300	$0.0001	–	4.3 s
Summarise a 30-page report	12,000 / 600	$0.0025	–	7.7 s
Code edit	6,000 / 1,500	$0.0015	–	17.9 s
Agentic coding session	60,000 / 4,000	$0.013	–	46.3 s
Structured extraction	2,000 / 200	$0.0004	–	3.1 s