Skip to content

72 listings across 65 models

Page 3 of 3. The lists below split this page's listings into those sold by Near AI, run by Near AI, or sent to Near AI by a marketplace.

Sold by Near AI

11 listings on this page sold by Near AI.

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
Qwen3.6 35B A3BQwen/Qwen3.6-35B-A3B-FP8 · fp8
$0.17cache read $0.056$1.10262K
qwen3-vl-30bQwen/Qwen3-VL-30B-A3B-Instruct
Not enough data yet$0.15cache read $0.03$0.5516KNot measured
Not enough data yet$0.01—33KNot enough data yetNot measured
Not enough data yet$1.00$1.00128KNot enough data yetNot measured
Not enough data yetNot enough data yet$0.01$0.00128KNot enough data yetNot measured
Not enough data yetNot enough data yet$0.01$0.0141KNot enough data yetNot measured
Not enough data yetNot enough data yet$0.01$0.01448Not measured
Not enough data yetNot enough data yet$0.04cache read $0.018$1.35262KNot enough data yetNot measured
Jev 1.13.0typesafe/jev-1.13
Doesn’t apply to this modelDoesn’t apply to this model$0.042Doesn’t apply to this model32KDoesn’t apply to this modelDoesn’t apply to this model
Levanto Sage 2levanto/sage-2
Doesn’t apply to this modelDoesn’t apply to this model$0.07Doesn’t apply to this model33KDoesn’t apply to this modelDoesn’t apply to this model
Not enough data yetNot enough data yet$0.30cache read $0.006$1.201MNot enough data yetNot measured

Run by Near AI

2 listings on this page where Near AI 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
GPT OSS 120B
 Hugging Face$0.03$0.15131K
GPT OSS 120Bfp4
 OpenRouter$0.03cache read $0.015$0.15131K

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

How this data works