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

Tool-use interaction evaluation on FTRL

36.33Solve P

MatchTIR (KM)

25.139628.044830.9533.8552Jan 15, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
36.3344.1837.3339.28
2026.01
34.4735.4433.534.47
2026.01
34.134.0731.5433.24
2026.01
33.6142.5633.6136.59
2026.01
33.2840.634.236.03
2026.01
32.3939.734.2135.43
2026.01
32.3238.8732.8534.68
2026.01
31.7937.5232.633.97
2026.01
31.5939.7532.5434.63
2026.01
31.1332.8330.6731.54
2026.01
30.936.2632.2833.15
2026.01
30.7829.6525.8528.76
2026.01
30.6440.0732.5134.41
2026.01
28.2628.3223.7826.79
2026.01
28.0836.5529.7431.46
2026.01
25.5735.3126.7229.2