Skip to content

Listings

All listings: 302ai

Every listing for the models on page 10 of 16 of 302ai, including each model's other versions and routes. Back to 302ai

Sold by 302ai

34 listings on this page sold by 302ai.

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
DeepSeek VL2
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
104.8
From 23 benchmarks. Plenty of data behind it.
Not enough data yet$0.142$0.1424KNot enough data yetNot measuredNot measured
Nova Lite
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
104.8
From 107 benchmarks. Plenty of data behind it.
β‰ˆ 82Β Β±10
Coding IQ 82.3, 95% interval 72–93. 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.
$0.06$0.24300K
41.5
Poor value (41.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
38 Β±9
Terse (38 Β±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
Qwen 2.5 14B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
104.8
From 147 benchmarks. Plenty of data behind it.
76Β Β±10stale
Coding IQ 75.7, 95% interval 65–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$0.10$0.1032KNot enough data yetNot measuredNot measured
Nova Micro
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035$0.14300K
47.4
Poor value (47.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen2-VL (72B) Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen2.5 VL 72B InstructWe compared release dates and version names in our catalogue.
103.1
From 34 benchmarks. Plenty of data behind it.
Not enough data yet$0.59$0.5932KNot enough data yetNot measuredNot measured
QwQ 32B Preview
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
102.9
From 103 benchmarks. Plenty of data behind it.
β‰ˆ 77Β Β±12
Coding IQ 76.8, 95% interval 64–89. 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.
$0.29$0.8633K
33.9
Poor value (33.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Claude 3 Haiku
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.
claude-3-haiku-20240307 Β· 20240307
102.7
From 315 benchmarks. Plenty of data behind it.
76Β Β±10
Coding IQ 75.9, 95% interval 66–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25cache read $0.05$1.25cache write $0.50200K
33.4
Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
117.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.1 70B
πŸ‡ΊπŸ‡Έ
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.
102.7
From 62 benchmarks. Plenty of data behind it.
Not enough data yet$1.50$1.50128KNot enough data yetNot measured
124.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 1.7B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
101.1
From 95 benchmarks. A fair amount of data behind it.
β‰ˆ 76Β Β±9
Coding IQ 75.7, 95% interval 66–85. 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.
$0.05$0.5029KNot enough data yetNot measuredNot measured
Qwen2.5-VL 7B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
100.7
From 78 benchmarks. Plenty of data behind it.
Not enough data yet$0.05$0.0532K
39.1
Poor value (39.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, 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.
ministral-3b-2512 Β· 2512
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.33$0.33256K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen2.5 Math 7B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
99.7
From 21 benchmarks. A fair amount of data behind it.
Not enough data yet$0.143$0.2864KNot enough data yetNot measuredNot measured
GPT-3.5 Turbo
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-4 TurboWe compared the version names in our catalogue.
gpt-3.5-turbo-0125 Β· 0125
99.4
From 417 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±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
Qwen2.5 7B 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.
98.8
From 248 benchmarks. Plenty of data behind it.
73Β Β±9stale
Coding IQ 73.2, 95% interval 64–82. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$0.05$0.0532K
54.3
Good value (54.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
qwen2.5-vl-3b-instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
98.6
From 46 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.60128KNot enough data yetNot measuredNot measured
Qwen2 57B A14B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
98.5
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.50$1.0064KNot enough data yetNot measuredNot measured
Qwen2 VL 7b Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen2.5-VL 7B InstructWe compared release dates and version names in our catalogue.
98.3
From 30 benchmarks. Plenty of data behind it.
Not enough data yet$0.29$0.7132KNot enough data yetNot measuredNot measured
Qwen2.5 Coder 7B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
98.0
From 59 benchmarks. Plenty of data behind it.
77Β Β±11stale
Coding IQ 76.6, 95% interval 66–87. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$0.05$0.0532K
54.5
Good value (54.5). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
DeepSeek R1 Distill Llama 70B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
97.6
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.80$0.8032KNot enough data yetNot measuredNot measured
Command R+
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
97.3
From 220 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±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.
$1.00$3.004KNot enough data yetNot measuredNot measured
Command R Plus
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
96.9
From 196 benchmarks. Plenty of data behind it.
Not enough data yet$3.00$15.00128K
21.9
Poor value (21.9). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.23$0.5832K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2024-08-09 Β· 2024-08-09
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$2.86$2.8632K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2024-10-30 Β· 2024-10-30
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$2.86$2.8632K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2024-11-19 Β· 2024-11-19
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.43$1.2932K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2024-12-30 Β· 2024-12-30
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.43$1.2932K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2025-01-25 Β· 2025-01-25
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.43$1.29128K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2025-04-02 Β· 2025-04-02
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.43$1.29128K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2025-04-08 Β· 2025-04-08
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.43$1.29128K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-2025-08-13 Β· 2025-08-13
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.23$0.58128K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen-VL Max
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen-vl-max-latest Β· latest
96.9
From 56 benchmarks. Plenty of data behind it.
Not enough data yet$0.23$0.572128K
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok 2 Vision 1212
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
1212
96.5
From 34 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$10.008K
31.4
Poor value (31.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Llama 3.1 8B Instruct
πŸ‡ΊπŸ‡Έ
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.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
95.6
From 343 benchmarks. Plenty of data behind it.
70Β Β±9
Coding IQ 69.9, 95% interval 61–79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.06$0.0632K
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Qwen2.5 Coder 1.5b Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
95.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”32KNot enough data yetNot measuredNot measured

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

How this data works