Skip to content

45 listings across 19 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policyTerms of service

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

Sold by Chutes

20 listings sold by Chutes.

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
Qwen4 Max
$1.50cache read $0.075$4.501MNot measuredNot measured
DeepSeek V4.1 Flash 1017
$0.195cache read $0.02$0.781M
Kimi K3moonshotai/Kimi-K3-TEE · tee · mxfp4
$1.85cache read $0.185$9.501M
Qwen3.8 MaxQwen/Qwen3.8-2.4T-A95B
$2.00cache read $0.25$6.001M
Qwen3.8 MaxQwen/Qwen3.8-Max-0902 · 0902
$2.00cache read $0.25$6.001M
GLM 5.3
$0.80cache read $0.16$2.501M
Hy 4
$0.525cache read $0.025$1.56251MNot measured
DeepSeek V4 Pro 0813
$0.85cache read $0.15$2.651M
GLM 5.2zai-org/GLM-5.2-Fast · fast
$2.45cache read $0.49$7.701M
GLM 5.2zai-org/GLM-5.2-TEE · tee · fp4
$1.25cache read $0.125$3.951M
Kimi K2.6moonshotai/Kimi-K2.6-TEE · tee · int4
$0.39cache read $0.039$1.80262K
DeepSeek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731-TEE · tee · fp8
$0.44cache read $0.044$1.321M
GLM 5.1zai-org/GLM-5.1-TEE · tee · fp8
$0.90cache read $0.09$2.90203K
Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B-TEE · tee · fp8
$0.45cache read $0.045$3.00262K
Qwen 3.8 27BQwen/Qwen3.8-27B-TEE · tee · fp8
$0.039cache read $0.0039$1.25262KNot measured
Kimi K2.7 Code
$0.832cache read $0.167$3.50262K
Qwen3.5 27BQwen/Qwen3.5-27B-TEE · tee · fp8
$0.20cache read $0.02$1.75262KNot measured
DeepSeek V3.2deepseek-ai/DeepSeek-V3.2-TEE · tee · fp8
$1.00cache read $0.10$1.00131KNot measured
Qwen3.6 27BQwen/Qwen3.6-27B-TEE · tee · fp8
$0.25cache read $0.025$2.00262KNot measured
gemma 4 31B turbo TEEtee · fp4
Not enough data yetNot enough data yet$0.12cache read $0.012$0.37131KNot enough data yetNot measuredNot measured

Run by Chutes

19 listings where Chutes 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 K3mxfp4 · 🇺🇸 US
 NanoGPT$1.9425cache read $0.1943$9.975Not published by the provider
Kimi K2.6int4 · 🇺🇸 US
 NanoGPT$0.4095cache read $0.041$1.89Not published by the provider
DeepSeek V4 Flash 0731fp8 · 🇺🇸 US
 NanoGPT$0.462cache read $0.0462$1.386Not published by the provider
GLM 5.1fp8 · 🇺🇸 US
 NanoGPT$0.945cache read $0.0945$3.045Not published by the provider
Qwen 3.8 27Bfp8 · 🇺🇸 US
 NanoGPT$0.041cache read $0.0041$1.3125Not published by the providerNot measured
Qwen3.5 27Bfp8 · 🇺🇸 US
 NanoGPT$0.21cache read $0.021$1.8375Not published by the providerNot measured
Qwen3.6 27Bfp8 · 🇺🇸 US
 NanoGPT$0.2625cache read $0.0263$2.10Not published by the providerNot measured
Show all 19 listings

Showing 7 of 19: one listing for each model.

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

How this data works