Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

TIR-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal Agent TaskTIR-Bench
Average@447.75
24
Tool-Integrated ReasoningTIR-Bench
Score20.8
4
Agentic ReasoningTIR-Bench
Accuracy19.8
3
Showing 3 of 3 rows