Skip to content

45 listings across 13 models

Data policies

from the provider's published policies

Privacy policyTerms of service

On training

We do not use Voice Samples, Voiceprints, user-uploaded images, prompts, generated Outputs, or other User Content to train, fine-tune, or improve any AI model, whether our own or any third party's.

Source: AkashML privacy policy

On keeping your data

not retained beyond the request lifecycle, except for transient error logs deleted within thirty (30) days.

Source: AkashML privacy policy

We take these statements from Akash's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.

Sold by Akash

8 listings sold by Akash.

Default order. 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
Kimi K3.1 Profp4
$1.75$10.001M
GLM 5.3fp4
$0.19$4.401M
Qwen 3.8 27Bfp8
$0.225$1.98262KNot measured
Qwen3.6 35B A3Bfp8
$0.10$0.90262KNot measured
GPT OSS 120Bfp4
$0.037$0.187131K
GPT OSS 20bfp4
$0.018$0.09131K
$0.20$0.52131KNot measured
Not enough data yet$0.00$0.00512Not enough data yetNot measuredNot measured

Run by Akash

30 listings where Akash runs the model. Another provider sells these listings.

Default order. 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
 Hugging Face$1.75$10.001M
GLM 5.3
 Hugging Face$0.19$4.401M
Qwen 3.8 27B
 Hugging Face$0.225$1.98262KNot measured
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it
 Hugging Face$0.07$0.24131K
 Hugging Face$0.10$0.90262KNot measured
GPT OSS 120B
 Hugging Face$0.03$0.187131K
GPT OSS 20b
 Hugging Face$0.018$0.09131K
 Hugging Face$0.20$0.52131KNot measured
Hermes Highfp4 · GLB
 NanoGPTNot enough data yetNot enough data yet$0.1995$4.62Not published by the providerNot enough data yetNot measuredNot measured
Hermes Lowfp4 · GLB
 NanoGPTNot enough data yetNot enough data yet$0.1995$4.62Not published by the providerNot enough data yetNot measuredNot measured
Hermes Mediumfp4 · GLB
 NanoGPTNot enough data yetNot enough data yet$0.1995$4.62Not published by the providerNot enough data yetNot measuredNot measured
Show all 30 listings

Showing 11 of 30: one listing for each model.

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

How this data works