Skip to content

68 listings across 13 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policyTerms of service

We haven't found any data policy statements on Wafer's pages yet.

Sold by Wafer

13 listings sold by Wafer.

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 Pro
$2.00cache read $0.20$10.001M
Kimi K3.1 ProKimi-K3.1-Pro-US · mxfp4 · 🇺🇸 us
$2.00cache read $0.20$10.001M
DeepSeek V4.1 Flash 1017mxfp4
$0.13cache read $0.01$0.501M
Kimi K3mxfp4
$0.60cache read $0.20$15.001M
GLM 5.3fp4
$0.20cache read $0.18$1.801M
DeepSeek V4.1 Flashmxfp4
$0.19cache read $0.012$0.651M
MiniMax M3.1 Flashnvfp4
$0.15cache read $0.02$0.601MNot measuredNot measured
GLM 5.2fp4
$0.19cache read $0.18$4.401M
GLM 5.3 Flashnvfp4
$0.05cache read $0.03$0.201M
DeepSeek V4 Flash 0731DeepSeek-V4-Flash-0731-Fast · fast · nvfp4
$0.13cache read $0.03$0.231M
DeepSeek V4 Pro
$0.28cache read $0.04$3.961M
Qwen 3.8 27B
$0.06cache read $0.05$2.30262KNot measured
DeepSeek V4 FlashDeepSeek-V4-Flash-0423 · 0423
$0.14cache read $0.03$0.281M

Run by Wafer

55 listings where Wafer 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
Kimi K3.1 Pro
 Hugging Face$0.253$8.801M
DeepSeek V4.1 Flash 1017
 Hugging Face$0.036$0.501M
Kimi K3
 Hugging Face$0.276$9.601M
GLM 5.3
 Hugging Face$0.0699$1.401M
DeepSeek V4.1 Flash
 Hugging Face$0.051$0.5671M
DeepSeek V4 Pro 0813
 Hugging Face$0.111$4.441M
MiniMax M3.1 Flash
 Hugging Face$0.135$0.541MNot measuredNot measured
GLM 5.2
 Hugging Face$0.007$6.801M
GLM 5.3 Flash
 Hugging Face$0.042$0.1841M
DeepSeek V4 Flash 0731
 Hugging Face$0.0443$0.301M
Qwen 3.8 27B🇺🇸 US
 NanoGPT$0.441cache read $0.0893$2.6775Not published by the providerNot measured
DeepSeek V4 Flash
 Hugging Face$0.12$0.171M
Hermes Highfp4 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$0.188cache read $0.1869$1.47Not published by the providerNot enough data yetNot measuredNot measured
Hermes Lowfp4 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$0.188cache read $0.1869$1.47Not published by the providerNot enough data yetNot measuredNot measured
Hermes Mediumfp4 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$0.188cache read $0.1869$1.47Not published by the providerNot enough data yetNot measuredNot measured
Show all 55 listings

Showing 15 of 55: one listing for each model.

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

How this data works