WISE-IoT LLM Leaderboard

Last Update:

Top 5 Models

Multitask (MMLU-Pro)
Coding (Human Eval)
Mathematics (GSM8K)
Reasoning (IFEval)
Tool Utilization (T-Eval)

Fastest and Most Affordable Models

Inter-token Latency (seconds)
End-to-End Latency (seconds)
Time to First Token (seconds)
Output Throughput (tokens/s)

Model Comparison

Models:vsConcurrent users:

Benchmark Comparison

ModelAverageMMLU-ProHumanEvalGSM8KIFEvalT-Eval