Saltar al contenido principal

Gemma 4 31B (Reasoning)

GoogleGemmaOpen WeightApache 2.0 · Uso Comercial

Descripción

Gemma 4 31B is Google DeepMind's flagship dense multimodal model with 31 billion parameters and a 256K context window. Ranks #3 among open models on Arena AI. Built from the same research as Gemini 3, it features Per-Layer Embeddings, Shared KV Cache, alternating sliding-window and global attention, and variable aspect ratio vision encoding. Achieves an estimated LMArena text score of 1452.

Fecha de lanzamiento
2026-04-02
Parámetros
30.7B
Longitud del contexto
262K
Modalidades
audio, image, text, video

Radar de capacidades

4
general
0
coding
70
reasoning
68
scienceest.
90
agents
70
multimodal

Science se estima a partir de las puntuaciones científicas de LLM Stats o del razonamiento cuando no hay benchmarks científicos dedicados.

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica39
58.0
LS
Ranking general66
4.0
AA
Ranking multimodal70
53.0
LS
Ciencia67
9.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench86.4%Aut.

Healthcare

MedXpertQA61.3%Aut.

Language

MMMLU88.4%Aut.
MMLU-Pro85.2%Aut.

Long Context

MRCR v2 (8-needle)66.4%Aut.

Math

AIME 202689.2%Aut.
MathVision85.6%Aut.

Reasoning

GPQANYU + Cohere + Anthropic (2023)84.3%Aut.
LiveCodeBench v680.0%Aut.
BIG-Bench Extra Hard74.4%Aut.
Humanity's Last Exam26.5%Aut.

Vision

MMMU-Pro76.9%Aut.

Índices de evaluación AA

(Artificial Analysis)
Engineering(Artificial Analysis)
11.9
Economics
9.5
Finance And Accounting
8.2
Legal
7.3
Strategy And Ops
6.9
Intelligence Index(Artificial Analysis)
4.4

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Legal
90
Finance
90
Agents
90
Tool Calling
90
Language
80
Physics
80
Biology
80
Chemistry
80
Math
70
Multimodal
70
Reasoning
70
General
70
Long Context
60
Healthcare
60
Vision
60

Precios

Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)$0.1525 / 1M tokens

Velocidad

Tokens/seg35.7
Retraso del primer token1.09s
Tiempo hasta la respuesta49.76s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

26 proveedores

Más barato: DeepInfraMás caro: AI/ML API
ProveedorEntradaSalida
1DeepInfraMás barato
$0.09
$0.34
2Adaption
$0.09
$0.34
3Kilo Gateway
$0.1
$0.34
4DevPass (LLM Gateway)
$0.1
$0.25
5FastRouter
$0.1
$0.3
6Kenari
$0.10286
$0.40571
7NanoGPT
$0.11
$0.33
8OrcaRouter
$0.13
$0.38
9FriendliAI
$0.14
$0.4
10Novita
$0.14
$0.4
11Abacus
$0.14
$0.4
12Novita AI
$0.14
$0.4
13Vercel AI Gateway
$0.14
$0.4
14Merge Gateway
$0.14
$0.4
15Crusoe
$0.14
$0.4
16Neuralwatt
$0.144
$0.42
17Keln
$0.15
$0.46
18Phala
$0.15
$0.46
19OpenRouter
$0.2
$0.4
20ai&
$0.2
$0.5
21Cortecs
$0.223
$0.39
22Powerspring
$0.23209
$0.40616
23Modular
$0.25
$0.65
24Together
$0.39
$0.97
25Opper
$0.46488
$2.44062
26AI/ML API
$1.04742
$1.57642

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas