Skip to content

Listings

All listings: OpenAI

Every listing for the models on page 3 of 7 of OpenAI, including each model's other versions and routes. Back to OpenAI

Sold by OpenAI

91 listings on this page sold by OpenAI.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
gpt-4.1-mini-batch · batch
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.80Not published by the provider
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
gpt-4.1-mini-2025-04-14-batch · batch+2025-04-14
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.80Not published by the provider
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.10batch $0.20$1.60batch $0.801M
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
gpt-4.1-mini-2025-04-14 · 2025-04-14
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.10batch $0.20$1.60batch $0.801M
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
gpt-5-nano-batch · batch
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.025$0.20Not published by the provider
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
gpt-5-nano-2025-08-07-batch · batch+2025-08-07
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.025$0.20Not published by the provider
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.005batch $0.025$0.40batch $0.20272K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
gpt-5-nano-2025-08-07 · 2025-08-07
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.005batch $0.025$0.40batch $0.20272K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
O1 Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versiono4 MiniWe compared release dates and version names in our catalogue.
115.3
From 187 benchmarks. Plenty of data behind it.
83 ±14
Coding IQ 82.8, 95% interval 69–97. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.55$4.40128K
32.5
Poor value (32.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
135.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
O1 Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versiono4 MiniWe compared release dates and version names in our catalogue.
o1-mini-2024-09-12 · 2024-09-12
115.3
From 187 benchmarks. Plenty of data behind it.
83 ±14
Coding IQ 82.8, 95% interval 69–97. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10$4.40Not published by the provider
32.5
Poor value (32.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
135.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
O1 Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versiono4 MiniWe compared release dates and version names in our catalogue.
o1-mini-batch · batch
115.3
From 187 benchmarks. Plenty of data behind it.
83 ±14
Coding IQ 82.8, 95% interval 69–97. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.55$2.20Not published by the provider
32.5
Poor value (32.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
135.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
O1 Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versiono4 MiniWe compared release dates and version names in our catalogue.
o1-mini-2024-09-12-batch · batch+2024-09-12
115.3
From 187 benchmarks. Plenty of data behind it.
83 ±14
Coding IQ 82.8, 95% interval 69–97. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.55$2.20Not published by the provider
32.5
Poor value (32.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
135.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o:extended · extended
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$6.00$18.00Not published by the provider
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-2024-05-13 · 2024-05-13
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00batch $2.50$15.00batch $7.50128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-batch · batch
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25$5.00Not published by the provider
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-2024-05-13-batch · batch+2024-05-13
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50$7.50Not published by the provider
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-2024-08-06-batch · batch+2024-08-06
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25$5.00Not published by the provider
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-2024-11-20-batch · batch+2024-11-20
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25$5.00Not published by the provider
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25batch $1.25$10.00batch $5.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-2024-08-06 · 2024-08-06
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25batch $1.25$10.00batch $5.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-2024-11-20 · 2024-11-20
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25batch $1.25$10.00batch $5.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-latest · latest
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$15.00Not published by the provider
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
111.6
From 224 benchmarks. Plenty of data behind it.
≈ 78 ±12
Coding IQ 77.7, 95% interval 66–90. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$30.00$60.008K
37.6
Poor value (37.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
121.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
gpt-4-0314 · 0314
111.6
From 224 benchmarks. Plenty of data behind it.
≈ 78 ±12
Coding IQ 77.7, 95% interval 66–90. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$30.00$60.00Not published by the provider
37.6
Poor value (37.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
121.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
gpt-4-0613 · 0613
111.6
From 224 benchmarks. Plenty of data behind it.
≈ 78 ±12
Coding IQ 77.7, 95% interval 66–90. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$30.00batch $15.00$60.00batch $30.008K
37.6
Poor value (37.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
121.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
gpt-4-batch · batch
111.6
From 224 benchmarks. Plenty of data behind it.
≈ 78 ±12
Coding IQ 77.7, 95% interval 66–90. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$30.00Not published by the provider
37.6
Poor value (37.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
121.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
gpt-4-0314-batch · batch+0314
111.6
From 224 benchmarks. Plenty of data behind it.
≈ 78 ±12
Coding IQ 77.7, 95% interval 66–90. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$30.00Not published by the provider
37.6
Poor value (37.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
121.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
gpt-4-0613-batch · batch+0613
111.6
From 224 benchmarks. Plenty of data behind it.
≈ 78 ±12
Coding IQ 77.7, 95% interval 66–90. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$30.00Not published by the provider
37.6
Poor value (37.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
121.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 20b
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±12
Coding IQ 88.2, 95% interval 76–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.029$0.14Not published by the provider
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Text Embedding 3 Large
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-embedding-3-large-batch · batch
109.5
From 117 benchmarks. Plenty of data behind it.
Not enough data yet$0.065—Not published by the providerNot enough data yetNot measuredNot measured
Text Embedding 3 Large
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
109.5
From 117 benchmarks. Plenty of data behind it.
Not enough data yet$0.13batch $0.065—8KNot enough data yetNot measuredNot measured
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-mini-batch · batch
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.075$0.30Not published by the provider
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-mini-2024-07-18-batch · batch+2024-07-18
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.075$0.30Not published by the provider
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075batch $0.075$0.60batch $0.30128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-mini-2024-07-18 · 2024-07-18
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075batch $0.075$0.60batch $0.30128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4 1106 Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5-previewWe compared the version names in our catalogue.
≈ 107
From 72 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$10.00$30.00128KNot enough data yetNot measuredNot measured
GPT 4 1106 Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5-previewWe compared the version names in our catalogue.
gpt-4-1106-preview-batch · batch
≈ 107
From 72 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$5.00$15.00Not published by the providerNot enough data yetNot measuredNot measured
GPT-3.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
gpt-3.5-0301 · 0301
≈ 106
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.50$2.00Not published by the providerNot enough data yetNot measuredNot measured
GPT-4-0125-preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5-previewWe compared the version names in our catalogue.
105.5
From 42 benchmarks. A fair amount of data behind it.
Not enough data yet$10.00$30.00Not published by the providerNot enough data yetNot measuredNot measured
GPT-4-0125-preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5-previewWe compared the version names in our catalogue.
gpt-4-0125-preview-batch · batch
105.5
From 42 benchmarks. A fair amount of data behind it.
Not enough data yet$5.00$15.00Not published by the providerNot enough data yetNot measuredNot measured
GPT-4.1 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared the version names in our catalogue.
105.3
From 325 benchmarks. Plenty of data behind it.
75 ±9
Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.025batch $0.05$0.40batch $0.201M
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared the version names in our catalogue.
gpt-4.1-nano-2025-04-14 · 2025-04-14
105.3
From 325 benchmarks. Plenty of data behind it.
75 ±9
Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.025batch $0.05$0.40batch $0.201M
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared the version names in our catalogue.
gpt-4.1-nano-batch · batch
105.3
From 325 benchmarks. Plenty of data behind it.
75 ±9
Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05$0.20Not published by the provider
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared the version names in our catalogue.
gpt-4.1-nano-2025-04-14-batch · batch+2025-04-14
105.3
From 325 benchmarks. Plenty of data behind it.
75 ±9
Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05$0.20Not published by the provider
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Sora 2 Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
≈ 102
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Text Davinci 003
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
≈ 101
From 14 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$20.00$20.00Not published by the providerNot enough data yetNot measuredNot measured
Text Davinci 003
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-davinci-003-batch · batch
≈ 101
From 14 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$10.00$10.00Not published by the providerNot enough data yetNot measuredNot measured
Text Embedding 3 Small
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-embedding-3-small-batch · batch
101.2
From 117 benchmarks. Plenty of data behind it.
Not enough data yet$0.01—Not published by the providerNot enough data yetNot measuredNot measured
Text Embedding 3 Small
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
101.2
From 117 benchmarks. Plenty of data behind it.
Not enough data yet$0.02batch $0.01—8KNot enough data yetNot measuredNot measured
Text Embedding Ada 002
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-embedding-ada-002-batch · batch
101.1
From 38 benchmarks. A fair amount of data behind it.
Not enough data yet$0.05—Not published by the providerNot enough data yetNot measuredNot measured
Text Embedding Ada 002
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-embedding-ada-002-v2-batch · batch+non-model
101.1
From 38 benchmarks. A fair amount of data behind it.
Not enough data yet$0.05—Not published by the providerNot enough data yetNot measuredNot measured
Text Embedding Ada 002
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-embedding-ada-002-v2 · non-model
101.1
From 38 benchmarks. A fair amount of data behind it.
Not enough data yet$0.10batch $0.05—8KNot enough data yetNot measuredNot measured
Text Embedding Ada 002
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
101.1
From 38 benchmarks. A fair amount of data behind it.
Not enough data yet$0.10—8KNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet$5.00cache read $1.25batch $2.50—Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
high+1024-x-1024
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
high+1024-x-1536
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
high+1536-x-1024
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
low+1024-x-1024
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
low+1024-x-1536
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
low+1536-x-1024
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
medium+1024-x-1024
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
medium+1024-x-1536
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
medium+1536-x-1024
100.1
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
low+1024-x-1024
100.1
From 23 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
low+1024-x-1536
100.1
From 23 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
low+1536-x-1024
100.1
From 23 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
medium+1024-x-1024
100.1
From 23 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
medium+1024-x-1536
100.1
From 23 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
medium+1536-x-1024
100.1
From 23 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
100.1
From 23 benchmarks. A fair amount of data behind it.
Not enough data yet$2.00cache read $0.20batch $1.00—Not published by the providerNot enough data yetNot measuredNot measured
Text Davinci 002
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
100.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yet$20.00$20.00Not published by the providerNot enough data yetNot measuredNot measured
Text Davinci 002
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-davinci-002-batch · batch
100.0
From 17 benchmarks. A fair amount of data behind it.
Not enough data yet$10.00$10.00Not published by the providerNot enough data yetNot measuredNot measured
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50$1.5016K
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-0613 · 0613
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50$2.0016K
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-1106 · 1106
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00batch $1.00$2.00batch $2.0016K
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-0125 · 0125
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50batch $0.25$1.50batch $0.7516K
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-0301 · 0301
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50$2.00Not published by the provider
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-batch · batch
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75$1.00Not published by the provider
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-0125-batch · batch+0125
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25$0.75Not published by the provider
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-0301-batch · batch+0301
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75$1.00Not published by the provider
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-0613-batch · batch+0613
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75$1.00Not published by the provider
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-3.5 Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-1106-batch · batch+1106
99.4
From 417 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50$1.00Not published by the provider
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
112.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
text-davinci-001
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
90.7
From 12 benchmarks. Plenty of data behind it.
Not enough data yet$20.00$20.00Not published by the providerNot enough data yetNot measuredNot measured
text-davinci-001
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
text-davinci-001-batch · batch
90.7
From 12 benchmarks. Plenty of data behind it.
Not enough data yet$10.00$10.00Not published by the providerNot enough data yetNot measuredNot measured
davinci
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
≈ 89
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$20.00$20.00Not published by the providerNot enough data yetNot measuredNot measured
davinci
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
davinci-batch · batch
≈ 89
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$10.00$10.00Not published by the providerNot enough data yetNot measuredNot measured
Sora 2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
88.3
From 9 benchmarks. A fair amount of data behind it.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
babbage
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
≈ 88
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.50$0.50Not published by the providerNot enough data yetNot measuredNot measured
babbage
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
babbage-batch · batch
≈ 88
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.25$0.25Not published by the providerNot enough data yetNot measuredNot measured
curie
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
≈ 88
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.00$2.00Not published by the providerNot enough data yetNot measuredNot measured
curie
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
curie-batch · batch
≈ 88
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.00$1.00Not published by the providerNot enough data yetNot measuredNot measured

Run by OpenAI

31 listings on this page where OpenAI runs the model. Another provider sells these listings.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
 Eden AI
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.10$1.601M
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
 Llmgateway
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.10$1.60Not published by the provider
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
 OpenRouter
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.10$1.601M
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
 Requesty
115.4
From 375 benchmarks. Plenty of data behind it.
91 ±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.10$1.601M
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
 Eden AI
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.005$0.40400K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
 Llmgateway
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.005$0.40Not published by the provider
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
 OpenRouter
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.005$0.40272K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
openai/gpt-5-nano:batch · batch
 OpenRouter
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.025cache read $0.0025$0.20400K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
flex
 OpenRouter
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.025cache read $0.0025$0.20272K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
 Requesty
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.005$0.40400K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
openai/gpt-5-nano:flex · flex
 Requesty
115.3
From 332 benchmarks. Plenty of data behind it.
93 ±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.025cache read $0.0025$0.20400K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Eden AI
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-2024-08-06 · 2024-08-06
 Eden AI
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-2024-11-20 · 2024-11-20
 Eden AI
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Llmgateway
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00Not published by the provider
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 OpenRouter
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-2024-08-06 · 2024-08-06
 OpenRouter
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-2024-11-20 · 2024-11-20
 OpenRouter
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Requesty
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-2024-05-13 · 2024-05-13
 Requesty
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-2024-08-06 · 2024-08-06
 Requesty
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-2024-11-20 · 2024-11-20
 Requesty
113.7
From 761 benchmarks. Plenty of data behind it.
77 ±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $1.25$10.00128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Text Embedding 3 Large
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Llmgateway
109.5
From 117 benchmarks. Plenty of data behind it.
Not enough data yet$0.13—Not published by the providerNot enough data yetNot measuredNot measured
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Eden AI
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Llmgateway
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60Not published by the provider
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 OpenRouter
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-mini-2024-07-18 · 2024-07-18
 OpenRouter
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Requesty
108.6
From 478 benchmarks. Plenty of data behind it.
72 ±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared the version names in our catalogue.
 Llmgateway
105.3
From 325 benchmarks. Plenty of data behind it.
75 ±9
Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.025$0.40Not published by the provider
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Text Embedding 3 Small
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Llmgateway
101.2
From 117 benchmarks. Plenty of data behind it.
Not enough data yet$0.02—Not published by the providerNot enough data yetNot measuredNot measured
Text Embedding Ada 002
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Llmgateway
101.1
From 38 benchmarks. A fair amount of data behind it.
Not enough data yet$0.10—Not published by the providerNot enough data yetNot measuredNot measured

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works