AgMoDB
Models
Agents
Evals
Explore
Tools
Industry
Menu
Gemma 4 31B (Reasoning) | AgMoDB
All Models
Gemma 4 31B (Reasoning)
April 2, 2026
Last synced Apr 7, 2026, 4:00 PM
Blended Price
Free/M
Input Price
Free/M
Output Price
Free/M
Speed
35 tok/s
TTFT
0.83s
Benchmark Scores
Intelligence Index
External Benchmarks
AA-Omniscience Index
Add to comparison
How Gemma 4 31B (Reasoning) 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
39.2
Coding Index
38.7
Math Index
—
MMLU Pro
—
/ 100
GPQA Diamond
0.9
/ 100
HLE
0.2
/ 100
LiveCodeBench
—
/ 100
SciCode
0.4
/ 100
MATH-500
—
/ 100
AIME
—
/ 30
AIME 2025
—
/ 30
IFBench
0.8
/ 100
LCR
0.6
/ 100
Terminal-Bench Hard
0.4
/ 100
τ²-Bench
0.6
/ 100
aa_omniscience
-45.4
/ 100
AA-Omniscience Accuracy
Predicted
41.6
/ 100
AA-Omniscience Hallucination Rate
Predicted
95.8
/ 100
Aider Polyglot
Predicted
86.5
/ 100
AIME
Predicted
0.9
/ 30
AIME 2025
Predicted
1.0
/ 30
AlpacaEval 2.0 LC
Predicted
30.2
/ 100
AlpacaEval 2.0 Raw
Predicted
23.3
/ 100
ARC-AGI-1
Predicted
64.1
/ 100
ARC-AGI-1 Cost per Task
Predicted
0.3
ARC-AGI-2
Predicted
11.7
/ 100
ARC-AGI-2 Cost per Task
Predicted
0.7
BFCL (Berkeley Function Calling)
Predicted
60.3
BigCodeBench Complete
Predicted
53.7
/ 100
BigCodeBench Instruct
Predicted
43.5
/ 100
AA Intelligence Index (Matrix)
Predicted
67.2
AA Long Context Reasoning (Matrix)
Predicted
73.6
AIME 2024
Predicted
99.1
AIME 2025 (Matrix)
Predicted
99.6
Arena-Hard Auto
Predicted
90.1
BrowseComp
Predicted
65.6
BRUMO 2025
Predicted
97.1
CMIMC 2025
Predicted
86.7
CritPt
Predicted
2.1
GPQA Diamond (Matrix)
Predicted
91.2
GSM8K
Predicted
97.0
HLE (Matrix)
Predicted
29.8
HMMT Feb 2025
Predicted
92.1
HMMT Nov 2025
Predicted
91.4
HumanEval
Predicted
93.7
IFBench (Matrix)
Predicted
63.5
IFEval
Predicted
92.7
IMO 2025
Predicted
29.8
LiveCodeBench (Matrix)
Predicted
86.5
MATH-500 (Matrix)
Predicted
98.8
MathArena Apex 2025
Predicted
2.1
MMLU
Predicted
91.0
MMLU-Pro (Matrix)
Predicted
86.8
MMMU-Pro
Predicted
82.2
MRCR v2
Predicted
78.3
OSWorld
Predicted
44.2
SimpleQA
Predicted
48.3
SMT 2025
Predicted
89.1
SWE-bench Pro
Predicted
41.7
Tau-Bench Telecom (Matrix)
Predicted
97.3
Terminal-Bench 2.0
Predicted
35.6
Terminal-Bench 1.0
Predicted
35.5
USAMO 2025
Predicted
24.2
Video-MMU
Predicted
86.8
browsecomp
Predicted
62.6
BullshitBench
Predicted
31.0
/ 100
Aider Polyglot
Predicted
0.1
Apex Agents
Predicted
2.4
Arc Agi 2
Predicted
0.0
BALROG
Predicted
0.0
BIG-Bench Hard
Predicted
3.0
BoolQ
Predicted
0.7
CAD-Eval
Predicted
2.4
Chess Puzzles
Predicted
0.2
CyBench
Predicted
0.6
DeepResearchBench
Predicted
0.4
FictionLiveBench
Predicted
0.8
Gdpval
Predicted
0.3
GeoBench
Predicted
0.0
GSM8K (Epoch)
Predicted
2.9
GSO
Predicted
0.0
HellaSwag
Predicted
0.0
Hle
Predicted
0.2
Lech Mazur Writing
Predicted
8.6
METR Time Horizons
Predicted
3.6
OTIS Mock AIME 2024–2025
Predicted
1.6
PIQA
Predicted
0.8
Posttrainbench
Predicted
0.0
SimpleQA Verified (Epoch)
Predicted
0.4
The Agent Company
Predicted
2.7
TriviaQA
Predicted
11.5
VPCT
Predicted
0.5
WinoGrande
Predicted
0.9
FrontierMath
Predicted
20.5
/ 100
GAIA Level 1
Predicted
88.2
GAIA Level 2
Predicted
84.5
GAIA Level 3
Predicted
97.3
GAIA
Predicted
77.5
/ 100
LegalBench
Predicted
89.6
/ 100
LiveCodeBench
Predicted
0.8
/ 100
LongBench v2 Easy
Predicted
67.4
LongBench v2 Hard
Predicted
51.4
LongBench v2
Predicted
46.7
/ 100
MATH-500
Predicted
1.0
/ 100
MathVista
Predicted
72.1
/ 100
MLE-bench
Predicted
44.6
/ 100
MMLU Pro
Predicted
0.9
/ 100
MMMU
Predicted
85.1
/ 100
MMTU Table Understanding
Predicted
68.1
/ 100
MT-Bench
Predicted
7.9
/ 10
NoLiMa (NIAH)
Predicted
95.3
/ 100
OCRBench v2
Predicted
87.3
/ 100
Open LLM Average
Predicted
19.5
/ 100
Open LLM: BBH
Predicted
49.9
/ 100
Open LLM: GPQA
Predicted
30.2
/ 100
Open LLM: IFEval
Predicted
35.5
/ 100
Open LLM: MATH Level 5
Predicted
9.5
/ 100
Open LLM: MMLU-PRO
Predicted
33.8
/ 100
Open LLM: MUSR
Predicted
41.6
/ 100
RE-Bench
Predicted
94.0
SimpleBench
Predicted
55.1
/ 100
simpleqa
Predicted
48.1
SWE-bench Lite
Predicted
60.4
/ 100
SWE-bench Verified
Predicted
76.9
/ 100
tau-bench Retail
Predicted
84.1
/ 100
Vectara Factual Consistency
Predicted
89.8
/ 100
Vectara Hallucination Rate
Predicted
10.2
/ 100
WebArena
Predicted
2.4
/ 100
WeirdML
Predicted
58.7
/ 100
WildBench
Predicted
47.7
LiveBench Coding
livebench
60.3
/ 100
LiveBench Data Analysis
livebench
58.8
/ 100
LiveBench Language
livebench
71.3
/ 100
LiveBench Math
livebench
73.9
/ 100
LiveBench Overall
livebench
61.6
/ 100
LiveBench Reasoning
livebench
59.4
/ 100