List your company

Tool Use Evaluation on ToolSandbox

0.923SimilarityWISE-Flow
0.390520.528760.6670.80524Jan 13, 2026Jan 27, 2026Feb 10, 2026Feb 24, 2026Mar 10, 2026Mar 24, 2026Apr 7, 2026

Evaluation results

MethodLinks
WISE-FlowModel=Qwen3-235B-A22B2026.010.9230.96153.6988—
REMEMBERERModel=Claude 3.7 Sonnet2026.010.9140.97282.4795—
AutoGuideModel=Qwen3-235B-A22B2026.010.9110.94845.0887—
ReActModel=Claude 3.7 Sonnet2026.010.9110.96033.7292—
AutoGuideModel=Claude 3.7 Sonnet2026.010.9110.96992.991—
WISE-FlowModel=Claude 3.7 Sonnet2026.010.910.97452.4695—
ReflexionModel=Claude 3.7 Sonnet2026.010.8750.94625.4287—
REMEMBERERModel=Qwen3-235B-A22B2026.010.8710.91348.5178—
LLM-onlyModel=Claude 3.7 Sonnet2026.010.8710.92776.9987—
ReflexionModel=Qwen3-235B-A22B2026.010.8660.89999.7984—
ReActModel=Qwen3-235B-A22B2026.010.8580.90089.776—
LLM-onlyModel=Qwen3-235B-A22B2026.010.8560.89859.7577—
TRACE2026.040.552———26
GEPA2026.040.52———22
GRPO on Target2026.040.519———22
Single Capability GRPO2026.040.514———22
AWM2026.040.504———20
ADP2026.040.422———19
BaseBackbone=Qwen3-30B-A3B2026.040.411———19