MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Open paper
Benchmark
Model
Rank
Results
deep-research-agents-on-browsecomp
MiroThinker-H1
–
Accuracy: 88.2
deep-research-agents-on-browsecomp-zh
MiroThinker-H1
–
Accuracy: 84.4
Rank counts only results with a code link.