Skip to content

105 listings across 40 models

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

Sold by Baseten

10 listings on this page sold by Baseten.

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
Nemotron 3 Ultranvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
$0.60cache read $0.12$2.40203K
$0.60$2.50Not published by the provider
GLM 4.6
$0.60$2.20Not published by the providerNot measured
MiniMax M2.5
$0.30$1.20Not published by the providerNot measured
Kimi K2 Instructbaseten/moonshotai/Kimi-K2-Instruct-0905 · 0905
$0.60$2.50Not published by the providerNot measuredNot measured
$0.50$1.50Not published by the providerNot measured
GPT OSS 120Bfp4
$0.10$0.50128K
DeepSeek V3baseten/deepseek-ai/DeepSeek-V3-0324 · 0324
$0.77$0.77Not published by the provider
Not enough data yetNot enough data yet$0.30$0.75Not published by the providerNot enough data yetNot measuredNot measured
Beam 1.0 501B A23Breflection/Beam-1.0 · fp4
Not enough data yetNot enough data yet$0.40cache read $0.04$1.201MNot enough data yetNot measuredNot measured

Run by Baseten

15 listings on this page where Baseten 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
Nemotron 3 Ultranvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · bf16
 Hugging Face$0.60$2.40203K
GPT OSS 120B
 Hugging Face$0.10$0.50128K
Beam 1.0 501B A23Breflection/beam-1.0 · fp4 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$1.365cache read $0.1365$4.515Not published by the providerNot enough data yetNot measuredNot measured
 OpenRouterDoesn’t apply to this modelDoesn’t apply to this model$0.10Doesn’t apply to this model33KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
Elephant 1
 OpenRouterDoesn’t apply to this modelDoesn’t apply to this model$0.035Doesn’t apply to this model16KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
 OpenRouterDoesn’t apply to this modelDoesn’t apply to this model$0.035Doesn’t apply to this model16KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
Hermes Highfp4 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$1.47cache read $0.147$4.62Not published by the providerNot enough data yetNot measuredNot measured
Hermes Lowfp4 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$1.47cache read $0.147$4.62Not published by the providerNot enough data yetNot measuredNot measured
Hermes Mediumfp4 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$1.47cache read $0.147$4.62Not published by the providerNot enough data yetNot measuredNot measured
Joey 1
 OpenRouterDoesn’t apply to this modelDoesn’t apply to this model$0.01Doesn’t apply to this model16KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
Mammoth 1
 OpenRouterDoesn’t apply to this modelDoesn’t apply to this model$0.10Doesn’t apply to this model16KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
Show all 15 listings

Showing 11 of 15: one listing for each model.

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

How this data works