Complex Reasoning on Frames
90.6AccuracyTongyi DeepResearch 30B
Evaluation Results
| Method | Links | |
|---|---|---|
| Tongyi DeepResearch 30BContext Window=128k, Memory Mechanism=Disabled2026.04 | 90.6 | |
| Claude-4.5-SonnetContext Window=128k, Memory Mechanism=Disabled2026.04 | 85 | |
| DeepSeek-V3.1Context Window=128k, Memory Mechanism=Disabled2026.04 | 83.7 | |
| LiteResearcher-4BContext Window=128k, Memory Mechanism=Disabled2026.04 | 83.1 | |
| SFR-DeepResearchContext Window=128k, Memory Mechanism=Disabled2026.04 | 82.8 | |
| AgentCPM-Explore-4BContext Window=128k, Memory Mechanism=Disabled2026.04 | 82.7 | |
| Claude-4-SonnetContext Window=128k, Memory Mechanism=Disabled2026.04 | 80.7 | |
| Mirothinker 8BContext Window=128k, Memory Mechanism=Disabled2026.04 | 80.6 | |
| DeepSeek-V3.2Context Window=128k, Memory Mechanism=Disabled2026.04 | 80.2 | |
| Kimi-ResearcherContext Window=128k, Memory Mechanism=Disabled2026.04 | 78.8 | |
| WebExplorer-8BContext Window=128k, Memory Mechanism=Disabled2026.04 | 75.7 | |
| ASearcher QWQ v2Context Window=128k, Memory Mechanism=Disabled2026.04 | 74.5 | |
| Kimi-K2-0905Context Window=128k, Memory Mechanism=Disabled2026.04 | 58.1 |