GPT-4o (Nov '24) Intelligence, Performance & Price Analysis

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).

Combination metric covering multiple dimensions of intelligence - the simplest way to compare how smart models are. Version 3.0 was released in September 2025 and includes: MMLU-Pro, GPQA Diamond, Humanity's Last Exam, LiveCodeBench, SciCode, AIME 2025, IFBench, AA-LCR, Terminal-Bench Hard, 𝜏²-Bench Telecom. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

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).

Combination metric covering multiple dimensions of intelligence - the simplest way to compare how smart models are. Version 3.0 was released in September 2025 and includes: MMLU-Pro, GPQA Diamond, Humanity's Last Exam, LiveCodeBench, SciCode, AIME 2025, IFBench, AA-LCR, Terminal-Bench Hard, 𝜏²-Bench Telecom. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

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).

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).

Combination metric covering multiple dimensions of intelligence - the simplest way to compare how smart models are. Version 3.0 was released in September 2025 and includes: MMLU-Pro, GPQA Diamond, Humanity's Last Exam, LiveCodeBench, SciCode, AIME 2025, IFBench, AA-LCR, Terminal-Bench Hard, 𝜏²-Bench Telecom. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Combination metric covering multiple dimensions of intelligence - the simplest way to compare how smart models are. Version 3.0 was released in September 2025 and includes: MMLU-Pro, GPQA Diamond, Humanity's Last Exam, LiveCodeBench, SciCode, AIME 2025, IFBench, AA-LCR, Terminal-Bench Hard, 𝜏²-Bench Telecom. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

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

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

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).

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).

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).

Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.

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).

Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

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).

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

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 to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

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).

Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

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).

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).

Seconds to receive a 500 token response considering input processing time, 'thinking' time of reasoning models, and 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).

Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

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).

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.

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.

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.