Step 3.7 Flash vs. Nemotron 3 Super 120B A12B (Reasoning)

Comparación entre Step 3.7 Flash y Nemotron 3 Super 120B A12B (Reasoning) según inteligencia, precio, velocidad, ventana de contexto y más.

Para más detalles sobre nuestra metodología, consulta la página de metodología.

Aspectos destacados

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

Comparación de modelos

Logo de StepFunStepFun
Step 3.7 Flash
Logo de NVIDIANVIDIA
Nemotron 3 Super 120B A12B (Reasoning)
Índice de Inteligencia
31
26
Step 3.7 Flash es más inteligente que Nemotron 3 Super 120B A12B (Reasoning)
Precio por millón de tokens
$0.18
$0.26
Step 3.7 Flash es más económico que Nemotron 3 Super 120B A12B (Reasoning)
Velocidad de salida
396 tokens/s
137 tokens/s
Step 3.7 Flash es más rápido que Nemotron 3 Super 120B A12B (Reasoning)
Tiempo hasta el primer token
0.82s
1.97s
Step 3.7 Flash responde más rápido que Nemotron 3 Super 120B A12B (Reasoning)
Ventana de contexto
262k tokens~393 páginas A4 con fuente Arial de tamaño 12
1000k tokens~1500 páginas A4 con fuente Arial de tamaño 12
Nemotron 3 Super 120B A12B (Reasoning) tiene una ventana de contexto más grande que Step 3.7 Flash
Fecha de lanzamiento
mayo de 2026
marzo de 2026
Step 3.7 Flash tiene una fecha de lanzamiento más reciente que la de Nemotron 3 Super 120B A12B (Reasoning)
Parámetros
198B, 11B activos durante la inferencia
120.6B, 12.7B activos durante la inferencia
Step 3.7 Flash tiene más parámetros que Nemotron 3 Super 120B A12B (Reasoning)
Razonamiento
Sí
Sí
Tanto Step 3.7 Flash como Nemotron 3 Super 120B A12B (Reasoning) son modelos de razonamiento
Entrada de imágenes
Sí
No
Step 3.7 Flash admite imágenes como entrada, mientras que Nemotron 3 Super 120B A12B (Reasoning) no
Pesos abiertos
Sí
Sí
Tanto Step 3.7 Flash como Nemotron 3 Super 120B A12B (Reasoning) tienen pesos abiertos
Licencia
Apache 2.0
Nvidia Nemotron Open Model License
La licencia permite el uso comercial sin restricciones
Sí
Sí
Tanto la licencia de Step 3.7 Flash como la de Nemotron 3 Super 120B A12B (Reasoning) permiten el uso comercial sin restricciones

Inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. 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

Artificial Analysis Intelligence Index v4.1.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more
GDPval-AA v2

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

𝜏³-BankingUpdated

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last ExamUpdated

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience AccuracyUpdated

Knowledge

AA-Omniscience Non-Hallucination RateUpdated

1 - hallucination rate

AA-LCRUpdated

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

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

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Briefcase

AA-Briefcase Elo

AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better
Reasoning models are indicated by a lightbulb icon

AA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.

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.
Reasoning models are indicated by a lightbulb icon

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)
Reasoning models are indicated by a lightbulb icon

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
Reasoning models are indicated by a lightbulb icon

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.

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Uso de tokens

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).

Costo

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

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.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

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)
Reasoning models are indicated by a lightbulb icon

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
Reasoning models are indicated by a lightbulb icon

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).

Velocidad

Medida por la velocidad de salida (tokens por segundo)

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better
Reasoning models are indicated by a lightbulb icon

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Latencia

Medida por el tiempo (segundos) hasta el primer token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time
Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Tiempo de respuesta de extremo a extremo

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better
Reasoning models are indicated by a lightbulb icon

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Tamaño del modelo (solo modelos de pesos abiertos)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

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

Step 3.7 Flash es más inteligente. Step 3.7 Flash obtiene 31, frente a los 26 de Nemotron 3 Super 120B A12B (Reasoning) en el Índice de Inteligencia de Artificial Analysis.

Step 3.7 Flash es más rápido. Step 3.7 Flash genera 395.8 tokens por segundo, frente a los 137.3 tokens por segundo de Nemotron 3 Super 120B A12B (Reasoning).

Step 3.7 Flash es más económico. Step 3.7 Flash cuesta $0.18 por millón de tokens, frente a Nemotron 3 Super 120B A12B (Reasoning), que cuesta $0.26 por millón de tokens (proporción 7:2:1 entre aciertos de caché, entrada y salida).

Step 3.7 Flash tiene menor latencia. El tiempo hasta el primer token de Step 3.7 Flash es de 0.82s, frente a los 1.97s de Nemotron 3 Super 120B A12B (Reasoning).

Nemotron 3 Super 120B A12B (Reasoning) tiene una ventana de contexto más grande. Nemotron 3 Super 120B A12B (Reasoning) admite 1.0M tokens, frente a los 260k tokens de Step 3.7 Flash.