Skip to content

79 listings across 50 models

Page 2 of 3. The lists below split this page's listings into those sold by Ionet, run by Ionet, or sent to Ionet by a marketplace.

Sold by Ionet

25 listings on this page sold by Ionet.

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
Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it Β· bf16
$0.0993cache read $0.0497$0.315262K
$0.11cache read $0.055$0.60cache write $0.22262KNot measuredNot measured
Kimi K2 Thinking
$0.60cache read $0.30$2.50262K
Qwen3.6 27B
$0.399cache read $0.1995$3.6733KNot measured
GLM 4.6
$0.496cache read $0.248$1.95131KNot measured
MiniMax M2.5
$0.287cache read $0.1435$1.126197KNot measured
DeepSeek R1deepseek-ai/DeepSeek-R1-0528 Β· 0528
$0.5237cache read $0.2618$2.2053128K
Kimi K2 Instructmoonshotai/Kimi-K2-Instruct-0905 Β· 0905
$0.57cache read $0.285$2.30262KNot measuredNot measured
MiniMax M2.7
$0.405cache read $0.2025$1.32262KNot measured
Qwen3.6 35B A3B
$0.13cache read $0.065$0.988262KNot measured
GPT OSS 120Bfp16
$0.168cache read $0.084$0.63131K
$0.0993cache read $0.0496$1.1825262KNot measuredNot measured
GLM 4.5 Air
$0.1567cache read $0.0783$0.9367131KNot measuredNot measured
Nemotron 3.5 Lightning
Not enough data yet$0.0513cache read $0.0256$0.17262KNot measuredNot measured
GLM 4.7 Flash
$0.0653cache read $0.0326$0.40200KNot measuredNot measured
Devstral Small 25052505
$0.05cache read $0.025$0.22cache write $0.10128KNot measuredNot measured
Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Β· fp8
$0.35cache read $0.175$1.075430K
GPT OSS 20b
$0.055cache read $0.0275$0.17664K
Qwen 2.5 VL 32B Instruct
Not enough data yet$0.05cache read $0.025$0.22cache write $0.1032KNot measuredNot measured
Not enough data yet$2.00cache read $1.00$6.00cache write $4.00128KNot enough data yetNot measuredNot measured
Magistral Small 2509mistralai/Magistral-Small-2506 Β· 2506
Not enough data yet$0.50cache read $0.25$1.50cache write $1.00128KNot measuredNot measured
Llama 3.3 70B Instruct
$0.4786cache read $0.2393$1.0946128KNot measured
Not enough data yet$0.35cache read $0.175$0.40cache write $0.7016KNot measuredNot measured
Mistral Nemomistralai/Mistral-Nemo-Instruct-2407
Not enough data yet$0.0568cache read $0.0284$0.06128KNot measured
Not enough data yetNot enough data yet$0.325cache read $0.1625$1.25106KNot enough data yetNot measuredNot measured

Run by Ionet

5 listings on this page where Ionet 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
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it
Β Hugging Face$0.067$0.29262K
Mistral Nemofp16
Β OpenRouterNot enough data yet$0.0166cache read $0.0108$0.0216128KNot measured
Show all 5 listings

Showing 2 of 5: one listing for each model.

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

How this data works