Skip to content

Listings

All listings: Microsoft Azure

Every listing for the models on page 4 of 13 of Microsoft Azure, including each model's other versions and routes. Back to Microsoft Azure

Sold by Microsoft Azure

62 listings on this page sold by Microsoft Azure.

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
ChatGPT-4o Latest
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
123.0
From 126 benchmarks. Plenty of data behind it.
≈ 86 ±13
Coding IQ 86.4, 95% interval 73–100. 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.
$5.00$15.00Not published by the provider
37.9
Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
ChatGPT-4o Latest
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
chatgpt-4o-latest-batch · batch
123.0
From 126 benchmarks. Plenty of data behind it.
≈ 86 ±13
Coding IQ 86.4, 95% interval 73–100. 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.
$2.50$7.50Not published by the provider
37.9
Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok 4.1 Fast
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
azure_ai/grok-4-1-fast-non-reasoning · non-reasoning
122.9
From 260 benchmarks. Plenty of data behind it.
95 ±14
Coding IQ 95.2, 95% interval 82–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.50128K
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 ±9
Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Grok 4.1 Fast
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
azure_ai/grok-4-1-fast-reasoning · reasoning
122.9
From 260 benchmarks. Plenty of data behind it.
95 ±14
Coding IQ 95.2, 95% interval 82–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$0.50128K
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 ±9
Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
Maker headquartered in CN, 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.
azure_ai/FW-MiniMax-M2.5
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.33cache read $0.033$1.321M
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
o3 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.
o3-mini-0131 · 0131
122.8
From 317 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.3, 95% interval 88–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.55batch $0.55$4.40batch $2.20Not published by the provider
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o3 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.
122.8
From 317 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.3, 95% interval 88–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.55batch $0.55$4.40batch $2.20200K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o3 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.
o3-mini-2025-01-31 · 2025-01-31 · 🇦🇺🇧🇷+18 australia-east, brazil-south +25
o3-mini-2025-01-31 · 2025-01-31 · 🇦🇺🇧🇷+18 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, italy-north, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, asia-pacific-southeast, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3
122.8
From 317 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.3, 95% interval 88–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.55batch $0.605$4.40batch $2.42200K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o3 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.
o3-mini-2025-01-31 · regional+2025-01-31
122.8
From 317 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.3, 95% interval 88–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.21cache read $0.605$4.84Not published by the provider
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o3 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.
o3-mini-2025-01-31 · us-eu-data-zone+2025-01-31 · 🇺🇸🇪🇺 us, eu
122.8
From 317 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.3, 95% interval 88–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.21cache read $0.605$4.84Not published by the provider
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o3 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.
o3-mini-batch · batch
122.8
From 317 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.3, 95% interval 88–102. Plenty 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
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o3 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.
o3-mini-2025-01-31-batch · batch+2025-01-31
122.8
From 317 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.3, 95% interval 88–102. Plenty 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
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$5.00cache write $1.25200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.3 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
🇦🇺🇧🇷+17 australia-east, brazil-south +23
🇦🇺🇧🇷+17 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3
122.4
From 61 benchmarks. A fair amount of data behind it.
Not enough data yet$1.75cache read $0.175$14.00112K
42.0
Poor value (42.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5.2 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
🇺🇸🇫🇷+5 us-central, us-east +11
🇺🇸🇫🇷+5 us-central, us-east, us-east-2, france-central, germany-west-central, us-north-central, poland-central, us-south-central, spain-central, sweden-central, europe-west, us-west, us-west-3
122.3
From 74 benchmarks. A fair amount of data behind it.
Not enough data yet$1.925cache read $0.1925$15.40112K
48.3
Fair value (48.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5.2 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
gpt-5.2-chat-latest · latest · 🇦🇺🇧🇷+16 australia-east, brazil-south +22
gpt-5.2-chat-latest · latest · 🇦🇺🇧🇷+16 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3
122.3
From 74 benchmarks. A fair amount of data behind it.
Not enough data yet$1.75cache read $0.175$14.00Not published by the provider
48.3
Fair value (48.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5.2 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
gpt-5.2-chat-latest-batch · batch+latest
122.3
From 74 benchmarks. A fair amount of data behind it.
Not enough data yet$0.875$7.00Not published by the provider
48.3
Fair value (48.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
🇦🇺🇧🇷+17 australia-east, brazil-south +24
🇦🇺🇧🇷+17 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-2, us-west-3
122.3
From 74 benchmarks. Plenty of data behind it.
Not enough data yet$1.25cache read $0.125$10.00128K
44.6
Poor value (44.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
gpt-5-chat-latest-batch · batch+latest
122.3
From 74 benchmarks. Plenty of data behind it.
Not enough data yet$0.625$5.00Not published by the provider
44.6
Poor value (44.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
gpt-5-chat-latest · latest
122.3
From 74 benchmarks. Plenty of data behind it.
Not enough data yet$1.25$10.00Not published by the provider
44.6
Poor value (44.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok 4 Fast
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
azure_ai/grok-4-fast-non-reasoning · non-reasoning
122.2
From 239 benchmarks. Plenty of data behind it.
91 ±16
Coding IQ 91.0, 95% interval 75–107. 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$0.50Not published by the provider
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4 Fast
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
azure_ai/grok-4-fast-reasoning · reasoning
122.2
From 239 benchmarks. Plenty of data behind it.
91 ±16
Coding IQ 91.0, 95% interval 75–107. 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$0.50Not published by the provider
65.9
Good value (65.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek R1
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
121.9
From 412 benchmarks. Plenty of data behind it.
93 ±14
Coding IQ 92.9, 95% interval 79–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.35$5.40Not published by the provider
36.1
Poor value (36.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
60 ±11
Chatty (60 ±11). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
140.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
121.9
From 268 benchmarks. Plenty of data behind it.
90 ±20
Coding IQ 90.1, 95% interval 71–110. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $7.50batch $7.50$60.00batch $30.00200K
26.4
Poor value (26.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o1-1217 · 1217
121.9
From 268 benchmarks. Plenty of data behind it.
90 ±20
Coding IQ 90.1, 95% interval 71–110. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $7.50batch $7.50$60.00batch $30.00Not published by the provider
26.4
Poor value (26.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o1-2024-12-17 · 2024-12-17 · 🇦🇺🇧🇷+18 australia-east, brazil-south +24
o1-2024-12-17 · 2024-12-17 · 🇦🇺🇧🇷+18 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, italy-north, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3
121.9
From 268 benchmarks. Plenty of data behind it.
90 ±20
Coding IQ 90.1, 95% interval 71–110. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $7.50batch $7.50$60.00batch $30.00200K
26.4
Poor value (26.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o1-2024-12-17 · regional+2024-12-17
121.9
From 268 benchmarks. Plenty of data behind it.
90 ±20
Coding IQ 90.1, 95% interval 71–110. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$16.50cache read $8.25$66.00Not published by the provider
26.4
Poor value (26.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o1-2024-12-17 · us-eu-data-zone+2024-12-17 · 🇺🇸🇪🇺 us, eu
121.9
From 268 benchmarks. Plenty of data behind it.
90 ±20
Coding IQ 90.1, 95% interval 71–110. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$16.50cache read $8.25$66.00Not published by the provider
26.4
Poor value (26.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o1-batch · batch
121.9
From 268 benchmarks. Plenty of data behind it.
90 ±20
Coding IQ 90.1, 95% interval 71–110. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$7.50$30.00Not published by the provider
26.4
Poor value (26.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
o1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o1-2024-12-17-batch · batch+2024-12-17
121.9
From 268 benchmarks. Plenty of data behind it.
90 ±20
Coding IQ 90.1, 95% interval 71–110. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$7.50$30.00Not published by the provider
26.4
Poor value (26.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.1 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
🇦🇺🇧🇷+17 australia-east, brazil-south +23
🇦🇺🇧🇷+17 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3
121.7
From 12 benchmarks. A fair amount of data behind it.
Not enough data yet$1.25cache read $0.125$10.00112K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5.1 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
gpt-5.1-chat-latest-batch · batch+latest
121.7
From 12 benchmarks. A fair amount of data behind it.
Not enough data yet$0.625$5.00Not published by the provider
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5.1 Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 ChatWe compared the version names in our catalogue.
gpt-5.1-chat-latest · latest
121.7
From 12 benchmarks. A fair amount of data behind it.
Not enough data yet$1.25$10.00Not published by the provider
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT 4.1
🇺🇸
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.
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50batch $1.00$8.00batch $4.001M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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-4.1-2025-04-14 · 2025-04-14 · 🇦🇺🇧🇷+18 australia-east, brazil-south +26
gpt-4.1-2025-04-14 · 2025-04-14 · 🇦🇺🇧🇷+18 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, italy-north, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, asia-pacific-southeast, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-2, us-west-3
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50batch $1.00$8.00batch $4.001M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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-4.1-2025-04-14 · data-zone+2025-04-14
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.55$8.80Not published by the provider
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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-4.1-2025-04-14 · regional+2025-04-14
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.55$8.80Not published by the provider
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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-4.1-batch · batch
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$4.00Not published by the provider
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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-4.1-2025-04-14-batch · batch+2025-04-14
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$4.00Not published by the provider
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3 Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
120.4
From 190 benchmarks. Plenty of data behind it.
≈ 95 ±12
Coding IQ 94.5, 95% interval 82–107. 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$1.27Not published by the provider
50.6
Fair value (50.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
139.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4 Nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
🇦🇺🇧🇷+17 australia-east, brazil-south +23
🇦🇺🇧🇷+17 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3
120.3
From 252 benchmarks. Plenty of data behind it.
104 ±6
Coding IQ 103.6, 95% interval 97–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.02batch $0.10$1.25batch $0.625272K
49.5
Fair value (49.5). Costs per task about what its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
146.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4 Nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
azure/gpt-5.4-nano-2026-03-17 · 2026-03-17
120.3
From 252 benchmarks. Plenty of data behind it.
104 ±6
Coding IQ 103.6, 95% interval 97–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.02batch $0.10$1.25batch $0.625272K
49.5
Fair value (49.5). Costs per task about what its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
146.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-Image-2.5 Flare
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-Image-2.6 FlareWe compared release dates and version names in our catalogue.
≈ 120
From 39 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$5.00cache read $1.25—Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-2.5 Sunburst
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-Image-2.6 SunburstWe compared release dates and version names in our catalogue.
≈ 120
From 39 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$5.00cache read $1.25—Not published by the providerNot enough data yetNot measuredNot measured
GPT 4 32k
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
≈ 120
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$60.00batch $30.00$120.00batch $60.00Not published by the providerNot enough data yetNot measuredNot measured
GPT 4 32k
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4-32k-0314 · 0314
≈ 120
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$60.00$120.00Not published by the providerNot enough data yetNot measuredNot measured
GPT 4 32k
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4-32k-0613 · 0613
≈ 120
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$60.00$120.00Not published by the providerNot enough data yetNot measuredNot measured
GPT 4 32k
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4-32k-batch · batch
≈ 120
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$30.00$60.00Not published by the providerNot enough data yetNot measuredNot measured
GPT 4 32k
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4-32k-0314-batch · batch+0314
≈ 120
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$30.00$60.00Not published by the providerNot enough data yetNot measuredNot measured
GPT 4 32k
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4-32k-0613-batch · batch+0613
≈ 120
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$30.00$60.00Not published by the providerNot enough data yetNot measuredNot measured
GPT-4.5 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-4.5-0227 · 0227
119.7
From 206 benchmarks. Plenty of data behind it.
88 ±11
Coding IQ 88.3, 95% interval 77–100. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$75.00cache read $37.50$150.00Not published by the provider
23.1
Poor value (23.1). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
136.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.5 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-4.5-preview-2025-02-27 · 2025-02-27 · 🇺🇸🇸🇪 us-east-2, sweden-central
119.7
From 206 benchmarks. Plenty of data behind it.
88 ±11
Coding IQ 88.3, 95% interval 77–100. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$75.00cache read $37.50$150.00Not published by the provider
23.1
Poor value (23.1). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
136.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V3.1
🇨🇳
Maker headquartered in CN, 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.
119.6
From 122 benchmarks. Plenty of data behind it.
94 ±8
Coding IQ 94.3, 95% interval 86–103. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.23$4.94Not published by the provider
44.0
Poor value (44.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Codex Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
≈ 119
From 9 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.50cache read $0.375$6.00200K
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Codex Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
codex-mini-latest-batch · batch+latest
≈ 119
From 9 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.75$3.00Not published by the provider
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Codex Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
codex-mini-latest · latest
≈ 119
From 9 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$1.50$6.00Not published by the provider
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Grok Code Fast 1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
118.4
From 31 benchmarks. Plenty of data behind it.
89 ±8
Coding IQ 88.7, 95% interval 81–96. 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$1.50256K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. A fair amount of data behind it.
43 ±9
Terse (43 ±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.
Not measured
GPT Image 1.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
🇦🇺🇧🇷+17 australia-east, brazil-south +23
🇦🇺🇧🇷+17 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3
118.3
From 56 benchmarks. A fair amount of data behind it.
Not enough data yet$5.00cache read $1.25$10.00Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
data-zone · 🇺🇸🇫🇷+6 us-central, us-east +12
data-zone · 🇺🇸🇫🇷+6 us-central, us-east, us-east-2, france-central, germany-west-central, us-north-central, europe-north, poland-central, us-south-central, spain-central, sweden-central, europe-west, us-west, us-west-3
118.3
From 56 benchmarks. A fair amount of data behind it.
Not enough data yet$5.50cache read $1.375$11.00Not published by the providerNot enough data yetNot measuredNot measured
GPT Image 1.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
azure/gpt-image-1.5-2025-12-16 · 2025-12-16
118.3
From 56 benchmarks. A fair amount of data behind it.
Not enough data yet$5.00cache read $1.25$10.00Not published by the providerNot enough data yetNot measuredNot measured
GPT OSS 120B
🇺🇸
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.
🇦🇺🇧🇷+21 australia-east, australia-southeast +38
🇦🇺🇧🇷+21 australia-east, australia-southeast, brazil-south, canada-central, canada-east, central-india, us-central, us-east, us-east-2, france-central, germany-west-central, indonesia-central, italy-north, japan-east, japan-west, korea-central, malaysia-west, us-north-central, europe-north, norway-east, poland-central, qatar-central, south-africa-north, us-south-central, asia-pacific-southeast, south-india, spain-central, sweden-central, switzerland-north, switzerland-west, uae-north, united-kingdom-south, united-kingdom-west, usgov-arizona, usgov-virginia, us-west-central, europe-west, us-west, us-west-2, us-west-3
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.082$0.60131K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
118.2
From 188 benchmarks. Plenty of data behind it.
≈ 91 ±10stale
Coding IQ 90.7, 95% interval 80–101. 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. Its newest result is over a year old.
$3.00$15.00Not published by the provider
34.0
Poor value (34.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
137.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

Run by Microsoft Azure

15 listings on this page where Microsoft Azure 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
Grok 4.1 Fast
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGrok 4.2 FastWe compared the version names in our catalogue.
grok-4-1-fast-reasoning · reasoning
 Llmgateway
122.9
From 260 benchmarks. Plenty of data behind it.
95 ±14
Coding IQ 95.2, 95% interval 82–109. 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$0.50Not published by the provider
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
56 ±9
Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
global
 OpenRouter
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$5.00cache write $1.25200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
 Cortecs AI
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
 Llmgateway
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$8.00Not published by the provider
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
 OpenRouter
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$8.001M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
 Requesty
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$8.001M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
azure/gpt-4.1@eastus2 · 🇺🇸 eastus2
 Requesty
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$8.001M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
azure/gpt-4.1@francecentral · 🇫🇷 francecentral
 Requesty
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.55$8.801M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
azure/gpt-4.1@swedencentral · 🇸🇪 swedencentral
 Requesty
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.55$8.801M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4.1
🇺🇸
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.
azure/gpt-4.1@westus3 · 🇺🇸 westus3
 Requesty
120.7
From 486 benchmarks. Plenty of data behind it.
92 ±6
Coding IQ 92.4, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$8.001M
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
33 ±8
Terse (33 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
136.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4 Nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Llmgateway
120.3
From 252 benchmarks. Plenty of data behind it.
104 ±6
Coding IQ 103.6, 95% interval 97–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.02$1.25Not published by the provider
49.5
Fair value (49.5). Costs per task about what its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
146.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4 Nano
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 OpenRouter
120.3
From 252 benchmarks. Plenty of data behind it.
104 ±6
Coding IQ 103.6, 95% interval 97–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.02$1.25400K
49.5
Fair value (49.5). Costs per task about what its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
146.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-Image-2.5 Flare
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-Image-2.6 FlareWe compared release dates and version names in our catalogue.
 Llmgateway
≈ 120
From 39 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$5.00cache read $1.25—Not published by the providerNot enough data yetNot measuredNot measured
GPT-Image-2.5 Sunburst
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-Image-2.6 SunburstWe compared release dates and version names in our catalogue.
 Llmgateway
≈ 120
From 39 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$5.00cache read $1.25—Not published by the providerNot enough data yetNot measuredNot measured
GPT OSS 120B
🇺🇸
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.
 Llmgateway
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15$0.60Not published by the provider
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

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

How this data works