List your company

Interactive Decision Making on ScienceWorld (test)

53.8ScoreMTRouter
-29.608-7.95413.735.354Apr 26, 2026

Evaluation results

MethodLinks
MTRouterRouting Level=Multi-Turn Routers (turn-level)2026.0453.85.7
GPT-5Routing Level=Single-Model Baselines2026.0448.413.9
Router-R1Routing Level=Multi-Turn Routers (turn-level)2026.0442.112.6
AvengersProRouting Level=Single-Turn Routers (episode-level)2026.0436.84.1
EmbedLLMRouting Level=Single-Turn Routers (episode-level)2026.0430.45.6
GPT-OSS-120BRouting Level=Single-Model Baselines2026.0426.60.5
RouterDCRouting Level=Single-Turn Routers (episode-level)2026.0423.13.3
Random RouterRouting Level=Multi-Turn Routers (turn-level)2026.0421.73.9
LLM RouterRouting Level=Multi-Turn Routers (turn-level)2026.0419.812.2
DeepSeek-V3.2Routing Level=Single-Model Baselines2026.0413.12.9
Kimi-K2Routing Level=Single-Model Baselines2026.045.22.5
Gemini-2.5-Flash-LiteRouting Level=Single-Model Baselines2026.044.20.3
MiniMax-M2Routing Level=Single-Model Baselines2026.04-0.53.2
OpenRouterRouting Level=Multi-Turn Routers (turn-level)2026.04-26.43