This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Sarvam has launched a newer model, Sarvam 30B (high). We suggest considering it instead.

For more information, see comparison of Sarvam 30B (high) to other models and API provider benchmarks for Sarvam 30B (high).

Sarvam

•

Open weights model

•

Released mayo de 2025

Análisis de inteligencia, rendimiento y precio de Sarvam M (Reasoning, based on Mistral Small 3.1)

Name: Inteligencia
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Probar Benchmarks de proveedores de API

InteligenciaUpdated

Índice de Inteligencia de Artificial Analysis

Velocidad

N/D

Tokens de salida por segundo

Costo

Entrada 0,00 US$Salida 0,00 US$

N/D

Costo por tarea del Índice de Inteligencia

Verbosidad

N/D

Tokens de salida del Índice de Inteligencia

Sarvam M (Reasoning, based on Mistral Small 3.1) está entre los modelos menos inteligentes, pero tiene un precio muy competitivo en comparación con otros modelos de pesos abiertos y tamaño similar. El modelo admite entrada de texto, genera texto y tiene una ventana de contexto de 33k tokens.

Sarvam M (Reasoning, based on Mistral Small 3.1) obtiene 5 puntos en el Índice de Inteligencia de Artificial Analysis, lo que lo sitúa en el extremo inferior entre modelos comparables (con una mediana de 8).

El precio de Sarvam M (Reasoning, based on Mistral Small 3.1) es de $0.00 por 1 M de tokens de entrada (muy competitivo; mediana: $0.04) y $0.00 por 1 M de tokens de salida (muy competitivo; mediana: $0.15).

Razonamiento	Sí Esta página muestra la versión con razonamiento de este modelo. También puede existir una variante sin razonamiento.
Modalidad de entrada	Admite: texto
Modalidad de salida	Admite: texto
Ventana de contexto	33k ~49 páginas A4 con fuente Arial de 12 puntos
Parámetros totales	23.6B
Licencia	Apache 2.0
Pesos del modelo	Hugging Face

Las métricas se comparan con modelos de la misma clase:

Modelos sin razonamiento → se comparan solo con otros modelos sin razonamiento
Modelos de razonamiento → se comparan tanto con modelos de razonamiento como sin razonamiento
Modelos de pesos abiertos → se comparan solo con otros modelos de pesos abiertos de la misma categoría de tamaño:

Muy pequeño: ≤4B parámetros
Pequeño: 4B–40B parámetros
Mediano: 40B–150B parámetros
Grande: >150B parámetros

Modelos propietarios → se comparan con modelos propietarios y de pesos abiertos del mismo rango de precio mediante una proporción combinada de precios de entrada/salida de 3:1:

<$0.15 por 1 M de tokens
$0.15–$1 por 1 M de tokens
>$1 por 1 M de tokens

Aspectos destacados

Updated

Inteligencia

Artificial Analysis Intelligence Index · Higher is better

Velocidad

Output tokens per second · Higher is better

Costo por tarea

Weighted average cost (USD) per Intelligence Index task · Lower is better

InteligenciaUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Estimate (independent evaluation forthcoming)

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

AA-Briefcase v1.1Updated

Agentic knowledge work, (Elo-500)/2000

GDPval-AA v2.1Updated

Agentic real-world work tasks, (Elo-500)/2000

AutomationBench-AAUpdated

Agentic SaaS workflows

Terminal-Bench 4.0New

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GDP.pdfNew

Professional document reasoning, All-pass

CritPtUnder review

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR v1.1

Long context reasoning

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

𝜏³-Banking

Agentic tool use

ITBench-AA

Kubernetes incident root-cause analysis

No data available

MMMU-Pro

Visual reasoning

MLCR-AANew

Medical long context reasoning

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

Índice de apertura

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Comparaciones del Índice de Inteligencia

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Costo

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Ventana de contexto

Context Window

Context window: tokens limit · Higher is better

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Tamaño del modelo (solo modelos de pesos abiertos)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Preguntas frecuentes

Preguntas comunes sobre Sarvam M (Reasoning, based on Mistral Small 3.1)

Sarvam M (Reasoning, based on Mistral Small 3.1) se lanzó el 23 de mayo de 2025.

Sarvam M (Reasoning, based on Mistral Small 3.1) fue creado por Sarvam.

Sarvam M (Reasoning, based on Mistral Small 3.1) obtiene 5 puntos (estimados) en el Índice de Inteligencia de Artificial Analysis, lo que lo sitúa en el extremo inferior entre otros modelos de pesos abiertos y tamaño similar (mediana: 8).

Sí, Sarvam M (Reasoning, based on Mistral Small 3.1) es un modelo de razonamiento. Usa pensamiento extendido o razonamiento en cadena para resolver problemas complejos antes de dar una respuesta.

Sarvam M (Reasoning, based on Mistral Small 3.1) admite entrada de texto.

Sarvam M (Reasoning, based on Mistral Small 3.1) admite salida de texto.

No, Sarvam M (Reasoning, based on Mistral Small 3.1) no admite imágenes como entrada. Solo puede procesar texto.

No, Sarvam M (Reasoning, based on Mistral Small 3.1) no es multimodal. Solo admite entradas de texto.

Sarvam M (Reasoning, based on Mistral Small 3.1) tiene una ventana de contexto de 33k tokens. Esto determina cuánto texto e historial de conversación puede procesar el modelo en una sola solicitud.

Sí, Sarvam M (Reasoning, based on Mistral Small 3.1) es un modelo de pesos abiertos. Los pesos del modelo están disponibles públicamente y pueden descargarse para alojarlo por cuenta propia.

Sarvam M (Reasoning, based on Mistral Small 3.1) tiene 23,6 mil millones de parámetros.

Sarvam M (Reasoning, based on Mistral Small 3.1) se publica bajo la licencia Apache 2.0, que permite el uso comercial. Ver licencia

Sarvam M (Reasoning, based on Mistral Small 3.1) obtiene 5 puntos en el Índice de Inteligencia de Artificial Analysis. Este benchmark compuesto evalúa los modelos en razonamiento, conocimiento, matemáticas y programación.

Sí, Sarvam M (Reasoning, based on Mistral Small 3.1) está disponible mediante API a través de 1 proveedor. Comparar proveedores de API

Sarvam M (Reasoning, based on Mistral Small 3.1) está disponible a través de 1 proveedor de API. Comparar proveedores

Análisis de inteligencia, rendimiento y precio de Sarvam M (Reasoning, based on Mistral Small 3.1)

Resumen del modelo

InteligenciaUpdated

Velocidad

Costo

Verbosidad

Resumen comparativo

Especificaciones técnicas

142 modelos en esta clase

Inteligencia

Velocidad

Costo por tarea

InteligenciaUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index

Open Weights

Benchmarks

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index

Índice de apertura

Artificial Analysis Openness Index: Score

Comparaciones del Índice de Inteligencia

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Costo

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Cache Hit

Ventana de contexto

Context Window

Context Window for RAG

Context Window

Tamaño del modelo (solo modelos de pesos abiertos)

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

Preguntas frecuentes

¿Cuándo se lanzó Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Quién creó Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Qué tan inteligente es Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Sarvam M (Reasoning, based on Mistral Small 3.1) es un modelo de razonamiento?

¿Qué modalidades de entrada admite Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Qué modalidades de salida admite Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Sarvam M (Reasoning, based on Mistral Small 3.1) puede procesar imágenes?

¿Sarvam M (Reasoning, based on Mistral Small 3.1) es multimodal?

¿Cuál es la ventana de contexto de Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Sarvam M (Reasoning, based on Mistral Small 3.1) es de código abierto?

¿Cuántos parámetros tiene Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Qué licencia tiene Sarvam M (Reasoning, based on Mistral Small 3.1)?

¿Cómo rinde Sarvam M (Reasoning, based on Mistral Small 3.1) en los benchmarks?

¿Sarvam M (Reasoning, based on Mistral Small 3.1) está disponible mediante API?

¿Dónde puedo usar Sarvam M (Reasoning, based on Mistral Small 3.1)?