AgMoDB
Models
Agents
Evals
Explore
Tools
Industry
Menu
DeepSeek V3.2 Speciale | AgMoDB
All Models
DeepSeek V3.2 Speciale
December 1, 2025
Last synced Apr 7, 2026, 4:00 PM
164K context
Blended Price
Free/M
Input Price
Free/M
Output Price
Free/M
Speed
0 tok/s
TTFT
0.00s
Benchmark Scores
Intelligence Index
External Benchmarks
AIME 2024
benchmark_matrix
Add to comparison
How DeepSeek V3.2 Speciale 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
29.4
Coding Index
37.9
Math Index
96.7
MMLU Pro
0.9
/ 100
GPQA Diamond
0.9
/ 100
HLE
0.3
/ 100
LiveCodeBench
0.9
/ 100
SciCode
0.4
/ 100
MATH-500
—
/ 100
AIME
—
/ 30
AIME 2025
1.0
/ 30
IFBench
0.6
/ 100
LCR
0.6
/ 100
Terminal-Bench Hard
0.3
/ 100
τ²-Bench
0.0
/ 100
96.0
AIME 2025 (Matrix)
benchmark_matrix
96.0
BRUMO 2025
benchmark_matrix
99.2
CMIMC 2025
benchmark_matrix
94.4
Codeforces Rating
benchmark_matrix
2701.0
GPQA Diamond (Matrix)
benchmark_matrix
85.7
HLE (Matrix)
benchmark_matrix
30.6
HMMT Feb 2025
benchmark_matrix
99.2
HMMT Nov 2025
benchmark_matrix
93.3
HumanEval
benchmark_matrix
91.5
IFEval
benchmark_matrix
88.0
IMO 2025
benchmark_matrix
83.3
LiveCodeBench (Matrix)
benchmark_matrix
88.7
MATH-500 (Matrix)
benchmark_matrix
98.0
MathArena Apex 2025
benchmark_matrix
9.4
MMLU-Pro (Matrix)
benchmark_matrix
87.5
SMT 2025
benchmark_matrix
89.2
SWE-bench Verified
benchmark_matrix
76.0
/ 100
AA-Omniscience Accuracy
Predicted
43.2
/ 100
AA-Omniscience Hallucination Rate
Predicted
97.1
/ 100
Aider Polyglot
Predicted
81.0
/ 100
AIME
Predicted
0.3
/ 30
AlpacaEval 2.0 LC
Predicted
24.5
/ 100
AlpacaEval 2.0 Raw
Predicted
19.1
/ 100
ARC-AGI-1
Predicted
79.8
/ 100
ARC-AGI-1 Cost per Task
Predicted
0.7
ARC-AGI-2
Predicted
37.5
/ 100
ARC-AGI-2 Cost per Task
Predicted
1.4
BFCL (Berkeley Function Calling)
Predicted
53.5
BigCodeBench Complete
Predicted
26.9
/ 100
BigCodeBench Instruct
Predicted
20.4
/ 100
AA Intelligence Index (Matrix)
Predicted
62.3
AA Long Context Reasoning (Matrix)
Predicted
81.5
Arena-Hard Auto
Predicted
80.6
BrowseComp
Predicted
75.1
CritPt
Predicted
7.6
GSM8K
Predicted
89.9
IFBench (Matrix)
Predicted
60.1
MMLU
Predicted
90.4
MMMU-Pro
Predicted
80.8
MRCR v2
Predicted
76.4
OSWorld
Predicted
38.0
SimpleQA
Predicted
55.7
SWE-bench Pro
Predicted
40.5
Tau-Bench Telecom (Matrix)
Predicted
98.3
Terminal-Bench 2.0
Predicted
54.4
Terminal-Bench 1.0
Predicted
43.0
USAMO 2025
Predicted
64.4
Video-MMU
Predicted
84.2
browsecomp
Predicted
74.3
BullshitBench
Predicted
40.7
/ 100
Aider Polyglot
Predicted
0.2
Apex Agents
Predicted
3.0
Arc Agi 2
Predicted
0.0
BALROG
Predicted
0.0
BIG-Bench Hard
Predicted
3.0
BoolQ
Predicted
0.7
CAD-Eval
Predicted
1.3
Chess Puzzles
Predicted
0.2
CyBench
Predicted
0.5
DeepResearchBench
Predicted
0.5
FictionLiveBench
Predicted
0.9
Gdpval
Predicted
0.5
GeoBench
Predicted
0.0
GSM8K (Epoch)
Predicted
3.0
GSO
Predicted
0.1
HellaSwag
Predicted
0.0
Hle
Predicted
0.3
Lech Mazur Writing
Predicted
8.5
METR Time Horizons
Predicted
16.6
OTIS Mock AIME 2024–2025
Predicted
0.8
PIQA
Predicted
0.7
Posttrainbench
Predicted
0.0
SimpleQA Verified (Epoch)
Predicted
0.5
The Agent Company
Predicted
2.7
TriviaQA
Predicted
15.0
VPCT
Predicted
0.3
WinoGrande
Predicted
0.9
FrontierMath
Predicted
29.2
/ 100
GAIA Level 1
Predicted
39.8
GAIA Level 2
Predicted
27.0
GAIA Level 3
Predicted
27.0
GAIA
Predicted
29.3
/ 100
LegalBench
Predicted
83.4
/ 100
LiveBench Coding
Predicted
66.0
/ 100
LiveBench Data Analysis
Predicted
64.3
/ 100
LiveBench Language
Predicted
84.5
/ 100
LiveBench Math
Predicted
88.1
/ 100
LiveBench Overall
Predicted
68.0
/ 100
LiveBench Reasoning
Predicted
71.9
/ 100
LongBench v2 Easy
Predicted
54.4
LongBench v2 Hard
Predicted
44.4
LongBench v2
Predicted
40.5
/ 100
MATH-500
Predicted
1.0
/ 100
MathVista
Predicted
70.4
/ 100
MedQA (USMLE)
Predicted
95.6
MMMU
Predicted
82.1
/ 100
MMTU Table Understanding
Predicted
65.0
/ 100
MT-Bench
Predicted
7.9
/ 10
NoLiMa (NIAH)
Predicted
88.9
/ 100
OCRBench v2
Predicted
82.1
/ 100
Open LLM Average
Predicted
20.5
/ 100
Open LLM: BBH
Predicted
53.0
/ 100
Open LLM: GPQA
Predicted
28.4
/ 100
Open LLM: IFEval
Predicted
34.3
/ 100
Open LLM: MATH Level 5
Predicted
5.0
/ 100
Open LLM: MMLU-PRO
Predicted
36.3
/ 100
Open LLM: MUSR
Predicted
40.7
/ 100
RE-Bench
Predicted
97.3
SimpleBench
Predicted
59.1
/ 100
simpleqa
Predicted
52.0
SWE-bench Lite
Predicted
70.1
/ 100
tau-bench Retail
Predicted
88.3
/ 100
Vectara Factual Consistency
Predicted
88.0
/ 100
Vectara Hallucination Rate
Predicted
12.0
/ 100
WebArena
Predicted
12.0
/ 100
WildBench
Predicted
40.4
MLE-bench
mlebench
56.4
/ 100
WeirdML
weirdml
46.7
/ 100