List your company
ResearchFormerly WizWand

Multi-turn dialogue on TopDial

7.71LLM-EVALBackbone
6.53486.83997.1457.4501Apr 9, 2026
Updated 7mo ago

Evaluation results

MethodLinks
BackboneBackbone=QWEN3-8B-INSTRUCT, Selection Method=Backbone2026.047.718.2514.50.3927.25
MDSBackbone=QWEN3-8B-INSTRUCT, Selection Method=MDS2026.047.327.7150.4511.25
RethinkingBackbone=QWEN3-8B-INSTRUCT, Selection Method=Rethinking2026.047.227.6211.20.4235.75
HeuristicBackbone=QWEN3-8B-INSTRUCT, Selection Method=Heuristic2026.047.217.5511.40.4125.67
SuperFilteringBackbone=QWEN3-8B-INSTRUCT, Selection Method=SuperFiltering2026.047.167.4111.70.4115.33
CC-ScoreBackbone=QWEN3-8B-INSTRUCT, Selection Method=CC-Score2026.047.167.4612.80.4314.75
Random DataBackbone=QWEN3-8B-INSTRUCT, Selection Method=Random Data2026.047.157.5213.40.4265.58
All DataBackbone=QWEN3-8B-INSTRUCT, Selection Method=All Data2026.047.147.5412.30.397.25
DialScoreBackbone=QWEN3-8B-INSTRUCT, Selection Method=DialScore2026.047.147.5611.60.4214.67
ZIPBackbone=QWEN3-8B-INSTRUCT, Selection Method=ZIP2026.047.137.58110.4146.17
BackboneBackbone=LLAMA3-8B-INSTRUCT, Selection Method=Backbone2026.047.126.6815.80.4995
MDSBackbone=LLAMA3-8B-INSTRUCT, Selection Method=MDS2026.047.126.4817.30.4651.25
SuperFilteringBackbone=LLAMA3-8B-INSTRUCT, Selection Method=SuperFiltering2026.046.986.2715.60.4584.92
HeuristicBackbone=LLAMA3-8B-INSTRUCT, Selection Method=Heuristic2026.046.976.215.10.4367
DialScoreBackbone=LLAMA3-8B-INSTRUCT, Selection Method=DialScore2026.046.96.2914.50.436
CC-ScoreBackbone=LLAMA3-8B-INSTRUCT, Selection Method=CC-Score2026.046.826.3815.10.4364.58
RethinkingBackbone=LLAMA3-8B-INSTRUCT, Selection Method=Rethinking2026.046.816.3614.40.4265.5
ZIPBackbone=LLAMA3-8B-INSTRUCT, Selection Method=ZIP2026.046.786.2815.30.4335.58
All DataBackbone=LLAMA3-8B-INSTRUCT, Selection Method=All Data2026.046.616.213.90.4095.67
Random DataBackbone=LLAMA3-8B-INSTRUCT, Selection Method=Random Data2026.046.586.2140.4096.92