Skip to content
Model Pulse

Lab

siliconflow

47 canonical models tracked · RSS feed for this lab

ModelBest in /MBest out /MContextProvidersReleased
baidu/ERNIE-4.5-300B-A47B$0.28$1.101
ByteDance-Seed/Seed-OSS-36B-Instruct$0.21$0.571
deepseek-ai/DeepSeek-R1$0.5$2.181
deepseek-ai/DeepSeek-V3$0.25$11
deepseek-ai/DeepSeek-V3.1$0.27$11
deepseek-ai/DeepSeek-V3.1-Terminus$0.27$11
deepseek-ai/DeepSeek-V3.2$0.27$0.421
deepseek-ai/DeepSeek-V3.2-Exp$0.27$0.411
DeepSeek V4 Flash$0.14$0.281
DeepSeek V4 Pro$1.74$3.481
Gemma 4 26B A4B IT$0.12$0.41
Gemma 4 31B IT$0.13$0.41
inclusionAI/Ling-flash-2.0$0.14$0.571
MiniMaxAI/MiniMax-M2.5$0.3$1.201
moonshotai/Kimi-K2.5$0.45$2.251
moonshotai/Kimi-K2.6$0.77$41
Qwen/Qwen2.5-72B-Instruct$0.59$0.591
Qwen/Qwen2.5-7B-Instruct$0.05$0.051
Qwen/Qwen3-14B$0.07$0.281
Qwen/Qwen3-235B-A22B-Thinking-2507$0.13$0.61
Qwen/Qwen3-30B-A3B-Instruct-2507$0.09$0.31
Qwen/Qwen3-32B$0.14$0.571
Qwen/Qwen3-8B$0.06$0.061
Qwen/Qwen3-Coder-30B-A3B-Instruct$0.07$0.281
Qwen/Qwen3-Coder-480B-A35B-Instruct$0.25$11
Qwen/Qwen3-VL-235B-A22B-Instruct$0.3$1.501
Qwen/Qwen3-VL-235B-A22B-Thinking$0.45$3.501
Qwen/Qwen3-VL-30B-A3B-Instruct$0.29$11
Qwen/Qwen3-VL-30B-A3B-Thinking$0.29$11
Qwen/Qwen3-VL-32B-Instruct$0.2$0.61
Qwen/Qwen3-VL-32B-Thinking$0.2$1.501
Qwen/Qwen3-VL-8B-Instruct$0.18$0.681
Qwen3.5 122B-A10B$0.26$2.081
Qwen3.5 27B$0.25$21
Qwen3.5 35B-A3B$0.24$1.801
Qwen3.5 397B-A17B$0.39$2.341
Qwen/Qwen3.5-9B$0.1$0.151
Qwen3.6 27B$0.3$3.201
Qwen3.6 35B-A3B$0.2$1.601
stepfun-ai/Step-3.5-Flash$0.1$0.31
tencent/Hunyuan-A13B-Instruct$0.14$0.571
Hy3 preview$0.066$0.261
zai-org/GLM-4.5-Air$0.14$0.861
zai-org/GLM-5$0.95$2.551
zai-org/GLM-5.1$1.40$4.401
GLM-5.2$1.40$4.401
zai-org/GLM-5V-Turbo$1.20$41