Climate Discovery on ClimaBench 2025
7.55AE ScoreDeepSeek-R1
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DeepSeek-R1Backbone=DeepSeek-R1-671B2026.04 | 7.55 | 4.35 | 8.65 | 5.38 | 6.48 | |
| Qwen3-235BBackbone=Qwen3-235B2026.04 | 7.58 | 4.4 | 8.62 | 5.42 | 6.52 | |
| GPT-4oBackbone=GPT-4o2026.04 | 7.72 | 3.8 | 8.85 | 5.82 | 6.55 | |
| ResearchAgentBackbone=GPT-4o2026.04 | 8.12 | 7.25 | 8.72 | 7.15 | 7.81 | |
| DS-AgentBackbone=DeepSeek-R1-671B2026.04 | 8.12 | 6.55 | 9.12 | 7.75 | 7.89 | |
| ResearchAgentBackbone=DeepSeek-R1-671B2026.04 | 8.15 | 6.92 | 8.95 | 7.72 | 7.94 | |
| DS-AgentBackbone=Qwen3-235B2026.04 | 8.15 | 6.58 | 9.15 | 7.78 | 7.92 | |
| ResearchAgentBackbone=Qwen3-235B2026.04 | 8.18 | 6.95 | 8.98 | 7.75 | 7.98 | |
| DS-AgentBackbone=GPT-4o2026.04 | 8.31 | 7.28 | 8.95 | 7.22 | 7.94 | |
| DeepAnalyzeBackbone=GPT-4o2026.04 | 8.58 | 6.35 | 8.82 | 6.88 | 7.48 | |
| DeepAnalyzeBackbone=DeepSeek-R1-671B2026.04 | 8.58 | 6.35 | 8.82 | 6.88 | 7.48 | |
| DeepAnalyzeBackbone=Qwen3-235B2026.04 | 8.58 | 6.35 | 8.82 | 6.88 | 7.48 | |
| Agent LaboratoryBackbone=GPT-4o2026.04 | 8.82 | 5.65 | 8.64 | 5.48 | 7.15 | |
| ClimAgentBackbone=GPT-4o2026.04 | 8.95 | 7.38 | 9.15 | 8.55 | 8.47 | |
| Agent LaboratoryBackbone=DeepSeek-R1-671B2026.04 | 8.95 | 5.68 | 8.95 | 5.75 | 7.33 | |
| Agent LaboratoryBackbone=Qwen3-235B2026.04 | 8.98 | 5.72 | 8.98 | 5.78 | 7.36 | |
| ClimAgentBackbone=DeepSeek-R1-671B2026.04 | 9.58 | 8.45 | 9.32 | 8.72 | 9.02 | |
| ClimAgentBackbone=Qwen3-235B2026.04 | 9.62 | 8.48 | 9.35 | 8.75 | 9.05 |