AgMoDB
Models
Agents
Evals
Explore
Tools
Industry
Menu
Ministral 3 14B | AgMoDB
All Models
Ministral 3 14B
December 2, 2025
Last synced Apr 7, 2026, 4:00 PM
Blended Price
$0.20/M
Input Price
$0.20/M
Output Price
$0.20/M
Speed
123 tok/s
TTFT
0.29s
Benchmark Scores
Intelligence Index
External Benchmarks
AA-Omniscience Accuracy
Add to comparison
How Ministral 3 14B Compares
Axes
X Axis
Blended Price (USD)
Y Axis
AgMoBench Overall
Bubble Size
Context Window
Filters
Blended Price (USD)
$0.00 – $30.0
AgMoBench Overall
≥ 3.5
Providers
ai21-labs
alibaba
anthropic
aws
azure
baidu
cohere
deepseek
+15 more
Table view
Filters
Show quadrants
Top models
anthropic
openai
google
meta
mistral
nvidia
kimi
xai
azure
deepseek
aws
cohere
baidu
ai21-labs
zai
reka-ai
xiaomi
alibaba
minimax
ibm
Bubble size = Context Window
16384.00
2000000.00
Compare with other models
16.0
Coding Index
10.9
Math Index
30.0
MMLU Pro
0.7
/ 100
GPQA Diamond
0.6
/ 100
HLE
0.0
/ 100
LiveCodeBench
0.4
/ 100
SciCode
0.2
/ 100
MATH-500
—
/ 100
AIME
—
/ 30
AIME 2025
0.3
/ 30
IFBench
0.3
/ 100
LCR
0.2
/ 100
Terminal-Bench Hard
0.0
/ 100
τ²-Bench
0.3
/ 100
Predicted
46.0
/ 100
AA-Omniscience Hallucination Rate
Predicted
97.1
/ 100
Aider Polyglot
Predicted
57.3
/ 100
AIME
Predicted
0.0
/ 30
AlpacaEval 2.0 LC
Predicted
23.1
/ 100
AlpacaEval 2.0 Raw
Predicted
18.2
/ 100
ARC-AGI-1
Predicted
63.9
/ 100
ARC-AGI-1 Cost per Task
Predicted
0.2
ARC-AGI-2
Predicted
10.4
/ 100
ARC-AGI-2 Cost per Task
Predicted
0.4
BFCL (Berkeley Function Calling)
Predicted
41.0
BigCodeBench Complete
Predicted
39.2
/ 100
BigCodeBench Instruct
Predicted
30.9
/ 100
AA Intelligence Index (Matrix)
Predicted
58.8
AA Long Context Reasoning (Matrix)
Predicted
75.3
AIME 2024
Predicted
90.1
AIME 2025 (Matrix)
Predicted
97.9
Arena-Hard Auto
Predicted
58.0
BrowseComp
Predicted
78.4
BRUMO 2025
Predicted
99.0
CMIMC 2025
Predicted
91.7
CritPt
Predicted
5.4
GPQA Diamond (Matrix)
Predicted
76.4
GSM8K
Predicted
91.3
HLE (Matrix)
Predicted
59.5
HMMT Feb 2025
Predicted
85.5
HMMT Nov 2025
Predicted
93.0
HumanEval
Predicted
85.9
IFBench (Matrix)
Predicted
51.5
IFEval
Predicted
86.6
IMO 2025
Predicted
37.5
LiveCodeBench (Matrix)
Predicted
66.2
MATH-500 (Matrix)
Predicted
95.9
MathArena Apex 2025
Predicted
6.4
MMLU
Predicted
85.7
MMLU-Pro (Matrix)
Predicted
77.7
MMMU-Pro
Predicted
79.0
MRCR v2
Predicted
80.1
OSWorld
Predicted
63.4
SimpleQA
Predicted
39.6
SMT 2025
Predicted
89.0
SWE-bench Pro
Predicted
49.6
Tau-Bench Telecom (Matrix)
Predicted
98.4
Terminal-Bench 2.0
Predicted
56.8
Terminal-Bench 1.0
Predicted
34.0
USAMO 2025
Predicted
17.1
Video-MMU
Predicted
85.4
browsecomp
Predicted
78.7
BullshitBench
Predicted
56.2
/ 100
Aider Polyglot
Predicted
1.6
Apex Agents
Predicted
3.3
Arc Agi 2
Predicted
0.3
BALROG
Predicted
0.0
BIG-Bench Hard
Predicted
3.0
BoolQ
Predicted
0.8
CAD-Eval
Predicted
4.3
Chess Puzzles
Predicted
0.3
CyBench
Predicted
0.3
DeepResearchBench
Predicted
0.4
FictionLiveBench
Predicted
0.7
Gdpval
Predicted
0.4
GeoBench
Predicted
0.0
GSM8K (Epoch)
Predicted
4.5
GSO
Predicted
0.1
HellaSwag
Predicted
0.0
Hle
Predicted
0.2
Lech Mazur Writing
Predicted
7.8
METR Time Horizons
Predicted
9.6
OTIS Mock AIME 2024–2025
Predicted
0.2
PIQA
Predicted
0.8
Posttrainbench
Predicted
0.0
SimpleQA Verified (Epoch)
Predicted
0.5
The Agent Company
Predicted
1.8
TriviaQA
Predicted
21.4
VPCT
Predicted
0.5
WinoGrande
Predicted
0.8
FrontierMath
Predicted
30.7
/ 100
GAIA Level 1
Predicted
45.5
GAIA Level 2
Predicted
16.3
GAIA Level 3
Predicted
1.1
GAIA
Predicted
29.9
/ 100
LegalBench
Predicted
61.8
/ 100
LiveBench Coding
Predicted
74.8
/ 100
LiveBench Data Analysis
Predicted
62.9
/ 100
LiveBench Language
Predicted
74.5
/ 100
LiveBench Math
Predicted
81.1
/ 100
LiveBench Overall
Predicted
67.4
/ 100
LiveBench Reasoning
Predicted
70.3
/ 100
LongBench v2 Easy
Predicted
44.6
LongBench v2 Hard
Predicted
36.9
LongBench v2
Predicted
38.2
/ 100
MATH-500
Predicted
0.8
/ 100
MathVista
Predicted
57.8
/ 100
MedQA (USMLE)
Predicted
81.2
MLE-bench
Predicted
53.7
/ 100
MMMU
Predicted
73.2
/ 100
MMTU Table Understanding
Predicted
58.3
/ 100
MT-Bench
Predicted
7.8
/ 10
NoLiMa (NIAH)
Predicted
90.5
/ 100
OCRBench v2
Predicted
74.5
/ 100
RE-Bench
Predicted
99.5
SimpleBench
Predicted
42.9
/ 100
simpleqa
Predicted
39.3
SWE-bench Lite
Predicted
29.4
/ 100
SWE-bench Verified
Predicted
58.8
/ 100
tau-bench Retail
Predicted
88.7
/ 100
WebArena
Predicted
0.4
/ 100
WeirdML
Predicted
42.7
/ 100
WildBench
Predicted
40.1
Arena ELO: Coding
chatbot_arena
194.0
Chatbot Arena ELO
chatbot_arena
3412.0
Open LLM Average
open_llm_leaderboard
17.2
/ 100
Open LLM: BBH
open_llm_leaderboard
47.0
/ 100
Open LLM: GPQA
open_llm_leaderboard
30.3
/ 100
Open LLM: IFEval
open_llm_leaderboard
27.9
/ 100
Open LLM: MATH Level 5
open_llm_leaderboard
7.6
/ 100
Open LLM: MMLU-PRO
open_llm_leaderboard
32.2
/ 100
Open LLM: MUSR
open_llm_leaderboard
41.5
/ 100
Vectara Factual Consistency
vectara_hallucination
80.6
/ 100
Vectara Hallucination Rate
vectara_hallucination
19.4
/ 100