List your company

Climate Discovery on ClimaBench 2025

7.55AE ScoreDeepSeek-R1
7.46728.02618.5859.1439Apr 18, 2026

Evaluation results

MethodLinks
DeepSeek-R1Backbone=DeepSeek-R1-671B2026.047.554.358.655.386.48
Qwen3-235BBackbone=Qwen3-235B2026.047.584.48.625.426.52
GPT-4oBackbone=GPT-4o2026.047.723.88.855.826.55
ResearchAgentBackbone=GPT-4o2026.048.127.258.727.157.81
DS-AgentBackbone=DeepSeek-R1-671B2026.048.126.559.127.757.89
ResearchAgentBackbone=DeepSeek-R1-671B2026.048.156.928.957.727.94
DS-AgentBackbone=Qwen3-235B2026.048.156.589.157.787.92
ResearchAgentBackbone=Qwen3-235B2026.048.186.958.987.757.98
DS-AgentBackbone=GPT-4o2026.048.317.288.957.227.94
DeepAnalyzeBackbone=GPT-4o2026.048.586.358.826.887.48
DeepAnalyzeBackbone=DeepSeek-R1-671B2026.048.586.358.826.887.48
DeepAnalyzeBackbone=Qwen3-235B2026.048.586.358.826.887.48
Agent LaboratoryBackbone=GPT-4o2026.048.825.658.645.487.15
ClimAgentBackbone=GPT-4o2026.048.957.389.158.558.47
Agent LaboratoryBackbone=DeepSeek-R1-671B2026.048.955.688.955.757.33
Agent LaboratoryBackbone=Qwen3-235B2026.048.985.728.985.787.36
ClimAgentBackbone=DeepSeek-R1-671B2026.049.588.459.328.729.02
ClimAgentBackbone=Qwen3-235B2026.049.628.489.358.759.05