Skip to content

639 listings across 229 models

Page 5 of 10. The lists below split this page's listings into those sold by Google, run by Google, or sent to Google by a marketplace.

Sold by Google

35 listings on this page sold by Google.

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
Llama 3.3 70B Instructvertex_ai/meta/llama-3.3-70b-instruct-maas · maas
$0.72batch $0.36$0.72batch $0.36128KNot measured
Not enough data yet$0.10—2KNot enough data yetNot measuredNot measured
Mistral Largevertex_ai/mistral-large@2407 · 2407
$2.00$6.00128KNot measured
Mistral Smallvertex_ai/mistral-small-2503@001 · 001+2503
$0.10$0.3032KNot measured
Llama 3.1 70B Instructvertex_ai/meta/llama-3.1-70b-instruct-maas · maas
——128KNot measuredNot measured
$0.075>128k $0.15$0.30>128k $0.60Not published by the providerNot measuredNot measured
Llama 4 Scoutvertex_ai/meta/llama-4-scout-17b-16e-instruct-maas · maas
$0.25batch $0.125$0.70batch $0.3510MNot measured
Gemini 1.5 Flash-8Bgemini-flash-1.5-8b
Not enough data yet$0.0375>128k $0.075cache read $0.01$0.15>128k $0.301MNot enough data yetNot measuredNot measured
Llama 3.2 90B Vision Instructvertex_ai/meta/llama-3.2-90b-vision-instruct-maas · maas
Not enough data yet——128KNot measuredNot measured
Not enough data yet$0.10—2KNot enough data yetNot measuredNot measured
Not enough data yet$2.00$8.00256KNot measuredNot measured
Gemini 2.5 Flash Image
Not enough data yet——66KNot measuredNot measured
Claude 3 Sonnet
$3.00$15.00200KNot measured
Not enough data yet$1.25>128k $2.50$5.00>128k $10.00Not published by the providerNot enough data yetNot measuredNot measured
Gemini Pro
Not enough data yet$0.125$0.37533KNot enough data yetNot measuredNot measured
Gemma 2 27B IT
$0.65$0.65Not published by the providerNot enough data yetNot measuredNot measured
Claude 3 Haiku
$0.25cache read $0.03$1.25cache write $0.30200KNot measured
Imagen 4 Ultraimagen-4.0-ultra-generate-001
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Veo 3.1 Fastgemini/veo-3.1-fast-generate-001
Not enough data yet——1KNot enough data yetNot measuredNot measured
gemini-1.5-flash-001
Not enough data yet$0.075>128k $0.15$0.30>128k $0.60Not published by the providerNot measuredNot measured
Not enough data yet$0.20$0.40256KNot measuredNot measured
Mistral Nemovertex_ai/mistral-nemo@2407 · 2407
Not enough data yet$3.00$3.00128KNot measured
Llama 3.1 8B Instructvertex_ai/meta/llama-3.1-8b-instruct-maas · maas
——128KNot measuredNot measured
Llama 3 8B Instructvertex_ai/meta/llama3-8b-instruct-maas · maas
——32KNot measuredNot measured
Imagen 3gemini/imagen-3.0-generate-001
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Show all 35 listings

Showing 25 of 35: one listing for each model.

Run by Google

22 listings on this page where Google 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
 OpenRouter$0.72$0.72128K
 LlmgatewayNot enough data yet$0.025—Not published by the providerNot enough data yetNot measured
Llama 4 Scoutus-east5
 OpenRouter$0.25$0.701.3M
 LlmgatewayNot enough data yet$0.025—Not published by the providerNot enough data yetNot measured
Gemini 2.5 Flash Image
 Eden AINot enough data yet$0.30cache read $0.03$2.5033KNot measured
Show all 22 listings

Showing 5 of 22: one listing for each model.

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

How this data works