List your company

Scientific Reasoning on SciWorld (Accuracy)

95.9AccuracyM2CL
33.18849.46965.7582.031Feb 2, 2026

Evaluation results

MethodLinks
M2CLModel=Qwen-72B, Number of LLMs=642026.0295.9
M2CLBackbone=Qwen-72B, Number of LLMs=322026.0295
M2CLBackbone=Qwen-72B, Number of LLMs=82026.0288.9
M2CLModel=Llama-70B, Number of LLMs=642026.0288.9
M2CLBackbone=Llama-70B, Number of LLMs=322026.0286
MacNetModel=Qwen-72B, Number of LLMs=642026.0285.1
M2CLBase Model=Qwen-72B, Number of LLMs=42026.0281.9
MacNetModel=Llama-70B, Number of LLMs=642026.0281.6
MacNetBackbone=Qwen-72B, Number of LLMs=322026.0279.5
MacNetBackbone=Llama-70B, Number of LLMs=322026.0276.6
M2CLBackbone=Llama-70B, Number of LLMs=82026.0276.2
DebateModel=Qwen-72B, Number of LLMs=642026.0269.1
MacNetBackbone=Qwen-72B, Number of LLMs=82026.0268.4
DebateBackbone=Qwen-72B, Number of LLMs=322026.0267.8
BoNModel=Qwen-72B, Number of LLMs=642026.0266
M2CLModel=Qwen-14B, Number of LLMs=642026.0265.8
M2CLBase Model=Llama-70B, Number of LLMs=42026.0265.5
DebateBackbone=Qwen-72B, Number of LLMs=82026.0265.2
MacNetBase Model=Qwen-72B, Number of LLMs=42026.0264.1
MacNetBackbone=Llama-70B, Number of LLMs=82026.0264
GPTSwarmModel=Qwen-72B, Number of LLMs=642026.0263.2
BoNBackbone=Qwen-72B, Number of LLMs=322026.0263.2
GPTSwarmBackbone=Qwen-72B, Number of LLMs=322026.0262.6
DebateBase Model=Qwen-72B, Number of LLMs=42026.0262.5
BoNBackbone=Qwen-72B, Number of LLMs=82026.0262.1
M2CLBackbone=Qwen-14B, Number of LLMs=322026.0262.1
GPTSwarmBackbone=Qwen-72B, Number of LLMs=82026.0260.2
DyLANModel=Qwen-72B, Number of LLMs=642026.0259.9
BoNBase Model=Qwen-72B, Number of LLMs=42026.0259.8
DyLANBackbone=Qwen-72B, Number of LLMs=322026.0259.1
GPTSwarmBase Model=Qwen-72B, Number of LLMs=42026.0259.1
DyLANBackbone=Qwen-72B, Number of LLMs=82026.0258
DyLANBase Model=Qwen-72B, Number of LLMs=42026.0257.8
MacNetModel=Qwen-14B, Number of LLMs=642026.0256.8
M2CLBackbone=Qwen-14B, Number of LLMs=82026.0256.1
MacNetBase Model=Llama-70B, Number of LLMs=42026.0255.9
MacNetBackbone=Qwen-14B, Number of LLMs=322026.0254.2
DebateModel=Llama-70B, Number of LLMs=642026.0253.5
M2CLModel=Qwen-7B, Number of LLMs=642026.0253.3
M2CLModel=Llama-14B, Number of LLMs=642026.0252.8
DebateBackbone=Llama-70B, Number of LLMs=322026.0252.1
M2CLBase Model=Qwen-14B, Number of LLMs=42026.0251.3
SingleBase Model=Qwen-72B, Number of LLMs=12026.0251.1
BoNModel=Llama-70B, Number of LLMs=642026.0251
M2CLBackbone=Llama-14B, Number of LLMs=322026.0250.7
SingleBackbone=Qwen-72B, Number of LLMs=82026.0250.4
M2CLBackbone=Qwen-7B, Number of LLMs=322026.0250.4
DebateBackbone=Llama-70B, Number of LLMs=82026.0250.1
BoNBackbone=Llama-70B, Number of LLMs=322026.0250.1
GPTSwarmModel=Llama-70B, Number of LLMs=642026.0249.3
SingleBackbone=Qwen-72B, Number of LLMs=322026.0249
BoNBackbone=Llama-70B, Number of LLMs=82026.0248.8
GPTSwarmBackbone=Llama-70B, Number of LLMs=322026.0248.4
SingleModel=Qwen-72B, Number of LLMs=642026.0248.3
DebateBase Model=Llama-70B, Number of LLMs=42026.0247.8
DyLANModel=Llama-70B, Number of LLMs=642026.0247.6
DyLANBackbone=Llama-70B, Number of LLMs=322026.0247.2
MacNetModel=Qwen-7B, Number of LLMs=642026.0246.7
BoNBase Model=Llama-70B, Number of LLMs=42026.0246.7
GPTSwarmBackbone=Llama-70B, Number of LLMs=82026.0246.5
DyLANBackbone=Llama-70B, Number of LLMs=82026.0246.4
MacNetBackbone=Qwen-14B, Number of LLMs=82026.0246
BoNModel=Qwen-14B, Number of LLMs=642026.0245.6
M2CLBackbone=Qwen-7B, Number of LLMs=82026.0245.3
GPTSwarmBase Model=Llama-70B, Number of LLMs=42026.0245.2
BoNBackbone=Qwen-14B, Number of LLMs=322026.0245.1
DyLANBase Model=Llama-70B, Number of LLMs=42026.0245.1
M2CLBackbone=Llama-14B, Number of LLMs=82026.0244.7
MacNetModel=Llama-14B, Number of LLMs=642026.0244.4
MacNetBackbone=Qwen-7B, Number of LLMs=322026.0243.1
M2CLModel=Llama-7B, Number of LLMs=642026.0242.9
DebateModel=Qwen-14B, Number of LLMs=642026.0242.7
MacNetBackbone=Llama-14B, Number of LLMs=322026.0241.7
DebateBackbone=Qwen-14B, Number of LLMs=322026.0241.7
M2CLBase Model=Qwen-7B, Number of LLMs=42026.0241.7
BoNBackbone=Qwen-14B, Number of LLMs=82026.0241.6
MacNetBase Model=Qwen-14B, Number of LLMs=42026.0241.4
M2CLBackbone=Llama-7B, Number of LLMs=322026.0240.7
SingleBase Model=Llama-70B, Number of LLMs=12026.0240.2
M2CLBase Model=Llama-14B, Number of LLMs=42026.0239.9
MacNetModel=Llama-7B, Number of LLMs=642026.0239.6
DebateBackbone=Qwen-14B, Number of LLMs=82026.0239.4
BoNBase Model=Qwen-14B, Number of LLMs=42026.0239.4
SingleBackbone=Llama-70B, Number of LLMs=82026.0239.1
BoNModel=Qwen-7B, Number of LLMs=642026.0238.6
SingleBackbone=Llama-70B, Number of LLMs=322026.0238.6
DebateBase Model=Qwen-14B, Number of LLMs=42026.0238.5
BoNBackbone=Qwen-7B, Number of LLMs=322026.0237.8
MacNetBackbone=Llama-7B, Number of LLMs=322026.0237.5
GPTSwarmBackbone=Qwen-14B, Number of LLMs=322026.0237.5
SingleModel=Llama-70B, Number of LLMs=642026.0237.3
MacNetBackbone=Qwen-7B, Number of LLMs=82026.0237
DyLANModel=Qwen-14B, Number of LLMs=642026.0237
DyLANBackbone=Qwen-14B, Number of LLMs=322026.0236.2
M2CLBackbone=Llama-7B, Number of LLMs=82026.0236.1
DyLANBackbone=Qwen-14B, Number of LLMs=82026.0236
GPTSwarmModel=Qwen-14B, Number of LLMs=642026.0236
GPTSwarmBackbone=Qwen-14B, Number of LLMs=82026.0235.9
BoNModel=Llama-14B, Number of LLMs=642026.0235.7
MacNetBackbone=Llama-14B, Number of LLMs=82026.0235.6