AgMoDB
Models
Agents
Evals
Explore
Tools
Industry
Menu
Gemini 3 Deep Think | AgMoDB
All Models
Gemini 3 Deep Think
February 5, 2026
Last synced Apr 7, 2026, 4:00 PM
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
ARC-AGI-1
Add to comparison
How Gemini 3 Deep Think 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
—
Coding Index
—
Math Index
—
MMLU Pro
—
/ 100
GPQA Diamond
—
/ 100
HLE
—
/ 100
LiveCodeBench
—
/ 100
SciCode
—
/ 100
MATH-500
—
/ 100
AIME
—
/ 30
AIME 2025
—
/ 30
IFBench
—
/ 100
LCR
—
/ 100
Terminal-Bench Hard
—
/ 100
τ²-Bench
—
/ 100
arc_agi
96.0
/ 100
ARC-AGI-1 Cost per Task
arc_agi
7.2
ARC-AGI-2
arc_agi
84.6
/ 100
ARC-AGI-2 Cost per Task
arc_agi
13.6
AA-Omniscience Accuracy
Predicted
49.7
/ 100
AA-Omniscience Hallucination Rate
Predicted
98.1
/ 100
Aider Polyglot
Predicted
80.1
/ 100
AIME
Predicted
0.0
/ 30
AIME 2025
Predicted
0.6
/ 30
AlpacaEval 2.0 LC
Predicted
16.2
/ 100
AlpacaEval 2.0 Raw
Predicted
13.0
/ 100
BFCL (Berkeley Function Calling)
Predicted
45.8
BigCodeBench Complete
Predicted
29.9
/ 100
BigCodeBench Instruct
Predicted
23.2
/ 100
AA Intelligence Index (Matrix)
Predicted
53.9
AA Long Context Reasoning (Matrix)
Predicted
78.3
AIME 2024
Predicted
97.7
AIME 2025 (Matrix)
Predicted
99.9
Arena-Hard Auto
Predicted
60.2
BrowseComp
Predicted
86.9
BRUMO 2025
Predicted
99.9
CMIMC 2025
Predicted
96.7
CritPt
Predicted
39.9
GPQA Diamond (Matrix)
Predicted
86.1
GSM8K
Predicted
92.9
HLE (Matrix)
Predicted
52.7
HMMT Feb 2025
Predicted
96.5
HMMT Nov 2025
Predicted
95.0
HumanEval
Predicted
92.5
IFBench (Matrix)
Predicted
65.3
IFEval
Predicted
89.7
IMO 2025
Predicted
63.2
LiveCodeBench (Matrix)
Predicted
78.0
MATH-500 (Matrix)
Predicted
97.5
MathArena Apex 2025
Predicted
23.5
MMLU
Predicted
89.7
MMLU-Pro (Matrix)
Predicted
85.7
MMMU-Pro
Predicted
78.6
MRCR v2
Predicted
83.4
OSWorld
Predicted
75.9
SimpleQA
Predicted
70.8
SMT 2025
Predicted
95.9
SWE-bench Pro
Predicted
58.8
Tau-Bench Telecom (Matrix)
Predicted
99.2
Terminal-Bench 2.0
Predicted
81.0
Terminal-Bench 1.0
Predicted
53.4
USAMO 2025
Predicted
33.2
Video-MMU
Predicted
85.0
browsecomp
Predicted
88.0
BullshitBench
Predicted
61.8
/ 100
Aider Polyglot
Predicted
0.3
Apex Agents
Predicted
4.3
BALROG
Predicted
0.0
BIG-Bench Hard
Predicted
3.0
BoolQ
Predicted
0.8
CAD-Eval
Predicted
3.2
Chess Puzzles
Predicted
0.4
CyBench
Predicted
0.7
DeepResearchBench
Predicted
0.5
FictionLiveBench
Predicted
0.9
Gdpval
Predicted
0.8
GeoBench
Predicted
0.0
GSM8K (Epoch)
Predicted
0.0
GSO
Predicted
2.0
HellaSwag
Predicted
0.0
Hle
Predicted
0.4
Lech Mazur Writing
Predicted
8.4
METR Time Horizons
Predicted
53.9
OTIS Mock AIME 2024–2025
Predicted
0.4
PIQA
Predicted
0.8
Posttrainbench
Predicted
0.0
SimpleQA Verified (Epoch)
Predicted
0.8
The Agent Company
Predicted
2.2
TriviaQA
Predicted
25.8
VPCT
Predicted
0.7
WinoGrande
Predicted
0.7
FrontierMath
Predicted
49.6
/ 100
GAIA Level 1
Predicted
56.7
GAIA Level 2
Predicted
21.0
GAIA Level 3
Predicted
4.6
GAIA
Predicted
39.0
/ 100
GPQA Diamond
Predicted
0.7
/ 100
HLE
Predicted
0.1
/ 100
IFBench
Predicted
0.6
/ 100
LCR
Predicted
0.1
/ 100
LegalBench
Predicted
45.6
/ 100
LiveBench Coding
Predicted
80.6
/ 100
LiveBench Data Analysis
Predicted
76.2
/ 100
LiveBench Language
Predicted
86.1
/ 100
LiveBench Math
Predicted
90.4
/ 100
LiveBench Overall
Predicted
80.7
/ 100
LiveBench Reasoning
Predicted
86.7
/ 100
LiveCodeBench
Predicted
0.4
/ 100
LongBench v2 Easy
Predicted
46.7
LongBench v2 Hard
Predicted
15.9
LongBench v2
Predicted
17.5
/ 100
MATH-500
Predicted
0.7
/ 100
MathVista
Predicted
52.3
/ 100
MedQA (USMLE)
Predicted
92.2
MLE-bench
Predicted
79.2
/ 100
MMLU Pro
Predicted
0.7
/ 100
MMMU
Predicted
79.0
/ 100
MMTU Table Understanding
Predicted
66.7
/ 100
MT-Bench
Predicted
7.7
/ 10
NoLiMa (NIAH)
Predicted
89.7
/ 100
OCRBench v2
Predicted
81.5
/ 100
Open LLM Average
Predicted
9.7
/ 100
Open LLM: BBH
Predicted
32.2
/ 100
Open LLM: GPQA
Predicted
24.9
/ 100
Open LLM: IFEval
Predicted
27.5
/ 100
Open LLM: MATH Level 5
Predicted
0.9
/ 100
Open LLM: MMLU-PRO
Predicted
18.2
/ 100
Open LLM: MUSR
Predicted
36.0
/ 100
RE-Bench
Predicted
100.0
SciCode
Predicted
0.1
/ 100
SimpleBench
Predicted
70.2
/ 100
simpleqa
Predicted
62.5
SWE-bench Lite
Predicted
44.8
/ 100
SWE-bench Verified
Predicted
80.9
/ 100
τ²-Bench
Predicted
0.8
/ 100
tau-bench Retail
Predicted
93.6
/ 100
Terminal-Bench Hard
Predicted
0.0
/ 100
Vectara Factual Consistency
Predicted
83.2
/ 100
Vectara Hallucination Rate
Predicted
16.8
/ 100
WebArena
Predicted
0.1
/ 100
WeirdML
Predicted
60.1
/ 100
WildBench
Predicted
37.1
Arc Agi 2
epoch_ai
0.5