Inference

terminalBench3

  • Not in index
  • Agentic
ModelsModels with a result.2
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.N/A

Results

2 results
#ModelResultThe score from the source.
—DeepSeek V4.1 Flash30.0%
—GLM-5.328.3%