Skip to content
LLM Pulse

Lab

nebius

32 canonical models tracked · RSS feed for this lab

ModelBest in /MBest out /MContextProvidersReleased
DeepSeek-V3.21
DeepSeek-V3.2-fast1
DeepSeek V4 Flash$0.14$0.281
DeepSeek V4 Pro$1.75$3.501
Gemma-3-27b-it$0.1$0.31
Llama-3.3-70B-Instruct$0.13$0.41
MiniMax-M2.5$0.3$1.201
MiniMax-M2.5-fast1
MiniMax-M3$0.3$1.201
Kimi-K2.51
Kimi-K2.5-fast1
Kimi K2.7 Code$0.95$41
Kimi K3$3$151
Hermes-4-405B$1$31
Hermes-4-70B$0.13$0.41
Llama-3.1-Nemotron-Ultra-253B-v1$0.6$1.801
Nemotron-3-Nano-Omni$0.06$0.241
Nemotron-3-Nano-30B-A3B$0.06$0.241
gpt-oss-120b-fast1
INTELLECT-31
Qwen2.5-VL-72B-Instruct$0.25$0.751
Qwen3 235B A22B Instruct 2507$0.2$0.61
Qwen3-235B-A22B-Thinking-2507-fast1
Qwen3-30B-A3B-Instruct-2507$0.1$0.31
Qwen3-32B$0.1$0.31
Qwen3-Embedding-8B$0.01$01
Qwen3-Next-80B-A3B-Thinking$0.15$1.201
Qwen3-Next-80B-A3B-Thinking-fast1
Qwen3.5-397B-A17B$0.6$3.601
Qwen3.5-397B-A17B-fast1
GLM-51
GLM-5.2$1.40$4.401