Scientific Discovery on MBO
153.53Solution QualityPIEVO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PIEVOBackbone=Gemini-2.5-Flash, Thinking Mode=Non-Thinking2026.02 | 153.53 | — | — | |
| PIEVOBackbone=Qwen3-32B, Thinking Mode=Non-Thinking2026.02 | 149.06 | — | — | |
| PiFlowBackbone=Qwen3-32B, Thinking Mode=Non-Thinking2026.02 | 96.1 | — | — | |
| PiFlowBackbone=Gemini-2.5-Flash, Thinking Mode=Non-Thinking2026.02 | 80.18 | — | — | |
| The AI Scientist v2Backbone=Qwen3-32B, Thinking Mode=Non-Thinking2026.02 | 76.56 | — | — | |
| Vanilla MASBackbone=Gemini-2.5-Flash, Thinking Mode=Non-Thinking2026.02 | 72.72 | — | — | |
| AI ResearcherBackbone=Qwen3-32B, Thinking Mode=Non-Thinking2026.02 | 69.72 | — | — | |
| ReActBackbone=Qwen3-32B, Thinking Mode=Non-Thinking2026.02 | 69.15 | — | — | |
| The AI Scientist v1Backbone=Qwen3-32B, Thinking Mode=Non-Thinking2026.02 | 66.41 | — | — | |
| ReActBackbone=Gemini-2.5-Flash, Thinking Mode=Non-Thinking2026.02 | 61.24 | — | — | |
| AI ResearcherBackbone=Gemini-2.5-Flash, Thinking Mode=Non-Thinking2026.02 | 61.22 | — | — | |
| The AI Scientist v2Backbone=Gemini-2.5-Flash, Thinking Mode=Non-Thinking2026.02 | 59.83 | — | — | |
| Vanilla MASBackbone=Qwen3-32B, Thinking Mode=Non-Thinking2026.02 | 57.57 | — | — | |
| The AI Scientist v1Backbone=Gemini-2.5-Flash, Thinking Mode=Non-Thinking2026.02 | 50.37 | — | — | |
| AI ResearcherBackbone LLM=Gemini-2.5-Flash, Thinking Mode=Non-thinking2026.02 | — | 6.9 | 49.1 | |
| AI ResearcherBackbone LLM=Qwen3-32B, Thinking Mode=Non-thinking2026.02 | — | 9 | 53 | |
| PIEVOBackbone LLM=Gemini-2.5-Flash, Thinking Mode=Non-thinking2026.02 | — | 28.3 | 122.3 | |
| PIEVOBackbone LLM=Qwen3-32B, Thinking Mode=Non-thinking2026.02 | — | 24.5 | 118.3 | |
| PiFlowBackbone LLM=Gemini-2.5-Flash, Thinking Mode=Non-thinking2026.02 | — | 14.4 | 52.8 | |
| PiFlowBackbone LLM=Qwen3-32B, Thinking Mode=Non-thinking2026.02 | — | 19 | 80.4 | |
| ReActBackbone LLM=Gemini-2.5-Flash, Thinking Mode=Non-thinking2026.02 | — | 7.3 | 54.9 | |
| ReActBackbone LLM=Qwen3-32B, Thinking Mode=Non-thinking2026.02 | — | 3.1 | 63.7 | |
| The AI Scientist v1Backbone LLM=Gemini-2.5-Flash, Thinking Mode=Non-thinking2026.02 | — | 3.3 | 43.5 | |
| The AI Scientist v1Backbone LLM=Qwen3-32B, Thinking Mode=Non-thinking2026.02 | — | 9.1 | 53.2 | |
| The AI Scientist v2Backbone LLM=Gemini-2.5-Flash, Thinking Mode=Non-thinking2026.02 | — | 6.5 | 50.1 | |
| The AI Scientist v2Backbone LLM=Qwen3-32B, Thinking Mode=Non-thinking2026.02 | — | 7.2 | 58.9 | |
| VanillaBackbone LLM=Gemini-2.5-Flash, Thinking Mode=Non-thinking2026.02 | — | 6 | 61.6 | |
| VanillaBackbone LLM=Qwen3-32B, Thinking Mode=Non-thinking2026.02 | — | 9.6 | 53.2 |