Skip to content

Listings

All listings: Aihubmix

Every listing for the models on page 7 of 20 of Aihubmix, including each model's other versions and routes. Back to Aihubmix

Sold by Aihubmix

42 listings on this page sold by Aihubmix.

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
MiniMax M2.5
πŸ‡¨πŸ‡³
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.
122.8
From 192 benchmarks. Plenty of data behind it.
100Β Β±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.
$0.288$1.152205K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 Β±9
Chatty (64 Β±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
πŸ‡¨πŸ‡³
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.
cc-minimax-m2.5 Β· cc
122.8
From 192 benchmarks. Plenty of data behind it.
100Β Β±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.
$0.10$0.10205K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 Β±9
Chatty (64 Β±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
πŸ‡¨πŸ‡³
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.
cc-minimax-m2.5-highspeed Β· cc+highspeed
122.8
From 192 benchmarks. Plenty of data behind it.
100Β Β±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.
$0.10$0.10205K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 Β±9
Chatty (64 Β±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
πŸ‡¨πŸ‡³
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.
coding-minimax-m2.5 Β· coding
122.8
From 192 benchmarks. Plenty of data behind it.
100Β Β±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.
$0.20$0.20205K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 Β±9
Chatty (64 Β±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
πŸ‡¨πŸ‡³
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.
coding-minimax-m2.5-free Β· coding+free
122.8
From 192 benchmarks. Plenty of data behind it.
100Β Β±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.
$0.00$0.00205K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 Β±9
Chatty (64 Β±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
πŸ‡¨πŸ‡³
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.
coding-minimax-m2.5-highspeed Β· coding+highspeed
122.8
From 192 benchmarks. Plenty of data behind it.
100Β Β±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.
$0.20$0.20205K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 Β±9
Chatty (64 Β±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
πŸ‡¨πŸ‡³
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.
minimax-m2.5-highspeed Β· highspeed
122.8
From 192 benchmarks. Plenty of data behind it.
100Β Β±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.
$0.288$1.152205K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 Β±9
Chatty (64 Β±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
πŸ‡ΊπŸ‡Έ
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.
95Β Β±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 $0.55$4.40200K
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
πŸ‡ΊπŸ‡Έ
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.
95Β Β±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.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±10
Chatty (59 Β±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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-5.3-chat-latest Β· latest
122.4
From 61 benchmarks. A fair amount of data behind it.
Not enough data yet$5.00cache read $0.50$30.00128K
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
πŸ‡ΊπŸ‡Έ
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 Β· latest
122.3
From 74 benchmarks. A fair amount of data behind it.
Not enough data yet$5.00cache read $0.50$30.00128K
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
πŸ‡ΊπŸ‡Έ
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 Β· latest
122.3
From 74 benchmarks. Plenty of data behind it.
Not enough data yet$5.00cache read $0.50$30.00128K
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
MiniMax M2.1
πŸ‡¨πŸ‡³
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.
122.3
From 97 benchmarks. Plenty of data behind it.
97Β Β±6
Coding IQ 96.5, 95% interval 91–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.288$1.152205K
45.1
Poor value (45.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±13
Chatty (59 Β±13). 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 M2.1
πŸ‡¨πŸ‡³
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.
cc-minimax-m2.1 Β· cc
122.3
From 97 benchmarks. Plenty of data behind it.
97Β Β±6
Coding IQ 96.5, 95% interval 91–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10$0.10205K
45.1
Poor value (45.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±13
Chatty (59 Β±13). 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 M2.1
πŸ‡¨πŸ‡³
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.
coding-minimax-m2.1 Β· coding
122.3
From 97 benchmarks. Plenty of data behind it.
97Β Β±6
Coding IQ 96.5, 95% interval 91–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.20205K
45.1
Poor value (45.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±13
Chatty (59 Β±13). 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 M2.1
πŸ‡¨πŸ‡³
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.
coding-minimax-m2.1-free Β· coding+free
122.3
From 97 benchmarks. Plenty of data behind it.
97Β Β±6
Coding IQ 96.5, 95% interval 91–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.00$0.00205K
45.1
Poor value (45.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±13
Chatty (59 Β±13). 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
GLM 4.5
πŸ‡¨πŸ‡³
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.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
121.9
From 110 benchmarks. Plenty of data behind it.
95Β Β±7
Coding IQ 95.3, 95% interval 88–103. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40$1.60131K
41.4
Poor value (41.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
53 Β±9
Typical (53 Β±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.
Not measured
o1
πŸ‡ΊπŸ‡Έ
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.
90Β Β±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 $7.50$60.00Not 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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o1-2024-12-17 Β· 2024-12-17
121.9
From 268 benchmarks. Plenty of data behind it.
90Β Β±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 $7.50$60.00Not 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
Qwen3.6 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.8 FlashWe compared release dates and version names in our catalogue.
121.9
From 108 benchmarks. Plenty of data behind it.
100Β Β±12
Coding IQ 100.2, 95% interval 88–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.169cache read $0.0169$1.014cache write $0.21131M
36.3
Poor value (36.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
60 Β±9
Chatty (60 Β±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.
143.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Doubao-Seed 1.6
Newer version
Newer versionDoubao Seed 1.8We compared the version names in our catalogue.
121.7
From 11 benchmarks. Plenty of data behind it.
Not enough data yet$0.1096cache read $0.0219$1.0959256K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Doubao-Seed 1.6
Newer version
Newer versionDoubao Seed 1.8We compared the version names in our catalogue.
doubao-seed-1-6-250615 Β· 250615
121.7
From 11 benchmarks. Plenty of data behind it.
Not enough data yet$0.1096cache read $0.0219$1.0959Not published by the provider
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Doubao-Seed 1.6
Newer version
Newer versionDoubao Seed 1.8We compared the version names in our catalogue.
doubao-seed-1-6-thinking Β· thinking
121.7
From 11 benchmarks. Plenty of data behind it.
Not enough data yet$0.1096cache read $0.0219$1.0959256K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Doubao-Seed 1.6
Newer version
Newer versionDoubao Seed 1.8We compared the version names in our catalogue.
doubao-seed-1-6-thinking-250615 Β· thinking+250615
121.7
From 11 benchmarks. Plenty of data behind it.
Not enough data yet$0.1096cache read $0.0219$1.0959Not published by the provider
48.2
Fair value (48.2). 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
πŸ‡ΊπŸ‡Έ
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 Β· latest
121.7
From 12 benchmarks. A fair amount of data behind it.
Not enough data yet$5.00cache read $0.50$30.00128K
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
Gemini 2.5 Flash
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared the version names in our catalogue.
gemini-2.5-flash-search Β· search
121.6
From 327 benchmarks. Plenty of data behind it.
86Β Β±16
Coding IQ 85.5, 95% interval 70–102. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30cache read $0.03$2.4991M
39.0
Poor value (39.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 Β±9
Chatty (57 Β±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.
141.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
LongCat 2.0
πŸ‡¨πŸ‡³
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.
Newer version
Newer versionLongCat 2.5We compared the version names in our catalogue.
121.5
From 5 benchmarks. A fair amount of data behind it.
Not enough data yet$0.7746cache read $0.0155$3.09841MNot enough data yetNot measuredNot measured
Qwen3.5 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.8 FlashWe compared release dates and version names in our catalogue.
121.5
From 110 benchmarks. Plenty of data behind it.
94Β Β±10
Coding IQ 94.0, 95% interval 85–104. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0282cache read $0.0028$0.282cache write $0.03531M
50.6
Fair value (50.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
62 Β±9
Chatty (62 Β±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
Qwen3 Max Preview
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionCoding Qwen4 Max PreviewWe compared release dates and version names in our catalogue.
121.5
From 90 benchmarks. A fair amount of data behind it.
β‰ˆ 93Β Β±12
Coding IQ 93.1, 95% interval 81–105. 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.
$0.846cache read $0.1692$3.384cache write $1.0575Not published by the provider
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M1 80K
πŸ‡¨πŸ‡³
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.
121.3
From 27 benchmarks. Plenty of data behind it.
Not enough data yet$0.60$2.40Not published by the providerNot enough data yetNot measuredNot measured
Gemini 2.5 Flash Preview 05-20 (no think)
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nothink
121.2
From 60 benchmarks. Plenty of data behind it.
Not enough data yet$0.30cache read $0.03$2.4991M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Gemini 2.5 Flash Preview 05-20 (no think)
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gemini-2.5-flash-preview-05-20-search Β· search
121.2
From 60 benchmarks. Plenty of data behind it.
Not enough data yet$0.30cache read $0.03$2.4991M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Qwen3.5 35B A3B
πŸ‡¨πŸ‡³
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.
Newer version
Newer versionQwen3.6 35B A3BWe compared release dates and version names in our catalogue.
121.1
From 311 benchmarks. Plenty of data behind it.
95Β Β±8
Coding IQ 95.0, 95% interval 87–103. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0564$0.4512262K
40.3
Poor value (40.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±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.
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2 Instruct
πŸ‡¨πŸ‡³
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.
121.0
From 184 benchmarks. Plenty of data behind it.
93Β Β±6
Coding IQ 93.0, 95% interval 87–99. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.54$2.16Not published by the provider
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Kimi K2 Instruct
πŸ‡¨πŸ‡³
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.
cc-kimi-k2-instruct Β· cc
121.0
From 184 benchmarks. Plenty of data behind it.
93Β Β±6
Coding IQ 93.0, 95% interval 87–99. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10$3.30Not published by the provider
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Kimi K2 Instruct
πŸ‡¨πŸ‡³
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.
cc-kimi-k2-instruct-0905 Β· cc+0905
121.0
From 184 benchmarks. Plenty of data behind it.
93Β Β±6
Coding IQ 93.0, 95% interval 87–99. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10$3.30Not published by the provider
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
GPT 4.1
πŸ‡ΊπŸ‡Έ
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.
92Β Β±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 Β±8
Terse (33 Β±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
Qwen3 235B A22B Instruct 2507
πŸ‡¨πŸ‡³
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.
120.7
From 258 benchmarks. Plenty of data behind it.
92Β Β±11
Coding IQ 92.4, 95% interval 82–103. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.28cache read $0.07$1.12262K
58.8
Good value (58.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
138
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 3 Mini
πŸ‡ΊπŸ‡Έ
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.
β‰ˆ 95Β Β±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.
$0.30$0.501Not 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
Grok 3 Mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-3-mini-beta Β· beta
120.4
From 190 benchmarks. Plenty of data behind it.
β‰ˆ 95Β Β±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.
$0.33$0.5511Not 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
Qwen3 VL 235B
πŸ‡¨πŸ‡³
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.
bai-qwen3-vl-235b-a22b-instruct
120.4
From 170 benchmarks. Plenty of data behind it.
β‰ˆ 94Β Β±18
Coding IQ 94.2, 95% interval 76–113. 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.
$0.274$1.096Not published by the provider
45.0
Poor value (45.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
GPT 5.4 Nano
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
120.3
From 252 benchmarks. Plenty of data behind it.
104Β Β±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 Β±9
Typical (47 Β±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

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

How this data works