AgMoDB
Models
Agents
Evals
Explore
Tools
Industry
Menu
Ministral 3 3B | AgMoDB
All Models
Ministral 3 3B
December 2, 2025
Last synced Apr 7, 2026, 4:00 PM
Blended Price
$0.10/M
Input Price
$0.10/M
Output Price
$0.10/M
Speed
296 tok/s
TTFT
0.28s
Benchmark Scores
Intelligence Index
External Benchmarks
AA-Omniscience Accuracy
Add to comparison
How Ministral 3 3B 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
11.2
Coding Index
4.8
Math Index
22.0
MMLU Pro
0.5
/ 100
GPQA Diamond
0.4
/ 100
HLE
0.1
/ 100
LiveCodeBench
0.2
/ 100
SciCode
0.1
/ 100
MATH-500
—
/ 100
AIME
—
/ 30
AIME 2025
0.2
/ 30
IFBench
0.3
/ 100
LCR
0.1
/ 100
Terminal-Bench Hard
0.0
/ 100
τ²-Bench
0.2
/ 100
Predicted
51.8
/ 100
AA-Omniscience Hallucination Rate
Predicted
97.9
/ 100
Aider Polyglot
Predicted
51.8
/ 100
AIME
Predicted
0.0
/ 30
AlpacaEval 2.0 LC
Predicted
14.5
/ 100
AlpacaEval 2.0 Raw
Predicted
11.8
/ 100
ARC-AGI-1
Predicted
92.8
/ 100
ARC-AGI-1 Cost per Task
Predicted
2.4
ARC-AGI-2
Predicted
84.4
/ 100
ARC-AGI-2 Cost per Task
Predicted
4.2
BFCL (Berkeley Function Calling)
Predicted
32.4
BigCodeBench Complete
Predicted
24.0
/ 100
BigCodeBench Instruct
Predicted
18.7
/ 100
AA Intelligence Index (Matrix)
Predicted
49.1
AA Long Context Reasoning (Matrix)
Predicted
78.7
AIME 2024
Predicted
84.2
AIME 2025 (Matrix)
Predicted
99.3
Arena-Hard Auto
Predicted
29.5
BrowseComp
Predicted
89.8
BRUMO 2025
Predicted
99.9
CMIMC 2025
Predicted
96.8
CritPt
Predicted
41.1
GPQA Diamond (Matrix)
Predicted
70.7
GSM8K
Predicted
84.2
HLE (Matrix)
Predicted
49.6
HMMT Feb 2025
Predicted
92.4
HMMT Nov 2025
Predicted
95.3
HumanEval
Predicted
77.8
IFBench (Matrix)
Predicted
54.0
IFEval
Predicted
83.7
IMO 2025
Predicted
62.7
LiveCodeBench (Matrix)
Predicted
57.9
MATH-500 (Matrix)
Predicted
93.7
MathArena Apex 2025
Predicted
32.1
MMLU
Predicted
69.5
MMLU-Pro (Matrix)
Predicted
51.1
MMMU-Pro
Predicted
76.5
MRCR v2
Predicted
83.6
OSWorld
Predicted
82.2
SimpleQA
Predicted
66.9
SMT 2025
Predicted
95.9
SWE-bench Pro
Predicted
61.8
Tau-Bench Telecom (Matrix)
Predicted
99.3
Terminal-Bench 2.0
Predicted
85.2
Terminal-Bench 1.0
Predicted
47.5
USAMO 2025
Predicted
23.3
Video-MMU
Predicted
84.1
browsecomp
Predicted
91.4
BullshitBench
Predicted
61.1
/ 100
Aider Polyglot
Predicted
0.1
Apex Agents
Predicted
4.9
Arc Agi 2
Predicted
1.6
BALROG
Predicted
0.0
BIG-Bench Hard
Predicted
3.0
BoolQ
Predicted
0.8
CAD-Eval
Predicted
5.0
Chess Puzzles
Predicted
0.5
CyBench
Predicted
0.4
DeepResearchBench
Predicted
0.5
FictionLiveBench
Predicted
0.6
Gdpval
Predicted
0.8
GeoBench
Predicted
0.0
GSM8K (Epoch)
Predicted
5.3
GSO
Predicted
4.0
HellaSwag
Predicted
0.0
Hle
Predicted
0.2
Lech Mazur Writing
Predicted
7.8
METR Time Horizons
Predicted
42.5
OTIS Mock AIME 2024–2025
Predicted
0.1
PIQA
Predicted
0.8
Posttrainbench
Predicted
0.0
SimpleQA Verified (Epoch)
Predicted
0.8
The Agent Company
Predicted
1.4
TriviaQA
Predicted
21.1
VPCT
Predicted
0.7
WinoGrande
Predicted
0.7
FrontierMath
Predicted
53.8
/ 100
GAIA Level 1
Predicted
21.0
GAIA Level 2
Predicted
2.5
GAIA Level 3
Predicted
0.0
GAIA
Predicted
12.4
/ 100
LegalBench
Predicted
24.1
/ 100
LiveBench Coding
Predicted
81.3
/ 100
LiveBench Data Analysis
Predicted
77.2
/ 100
LiveBench Language
Predicted
87.0
/ 100
LiveBench Math
Predicted
91.1
/ 100
LiveBench Overall
Predicted
81.4
/ 100
LiveBench Reasoning
Predicted
87.2
/ 100
LongBench v2 Easy
Predicted
35.8
LongBench v2 Hard
Predicted
27.3
LongBench v2
Predicted
25.5
/ 100
MATH-500
Predicted
0.6
/ 100
MathVista
Predicted
19.5
/ 100
MedQA (USMLE)
Predicted
74.4
MLE-bench
Predicted
78.6
/ 100
MMMU
Predicted
67.9
/ 100
MMTU Table Understanding
Predicted
59.2
/ 100
MT-Bench
Predicted
7.7
/ 10
NoLiMa (NIAH)
Predicted
84.3
/ 100
OCRBench v2
Predicted
59.6
/ 100
Open LLM Average
Predicted
10.7
/ 100
Open LLM: BBH
Predicted
32.2
/ 100
Open LLM: GPQA
Predicted
24.6
/ 100
Open LLM: IFEval
Predicted
37.6
/ 100
Open LLM: MATH Level 5
Predicted
2.8
/ 100
Open LLM: MMLU-PRO
Predicted
18.2
/ 100
Open LLM: MUSR
Predicted
35.2
/ 100
RE-Bench
Predicted
100.0
SimpleBench
Predicted
62.4
/ 100
simpleqa
Predicted
54.9
SWE-bench Lite
Predicted
22.4
/ 100
SWE-bench Verified
Predicted
69.5
/ 100
tau-bench Retail
Predicted
94.3
/ 100
WebArena
Predicted
0.0
/ 100
WeirdML
Predicted
39.8
/ 100
WildBench
Predicted
35.3
Vectara Factual Consistency
vectara_hallucination
75.8
/ 100
Vectara Hallucination Rate
vectara_hallucination
24.2
/ 100