Complex Reasoning on Seal-0
53.4Accuracy (Seal-0)Claude-4.5-Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude-4.5-SonnetContext Window=128k, Memory Mechanism=Disabled2026.04 | 53.4 | |
| OpenAI-GPT-5-highContext Window=128k, Memory Mechanism=Disabled2026.04 | 51.4 | |
| LiteResearcher-4BContext Window=128k, Memory Mechanism=Disabled2026.04 | 41.8 | |
| AgentCPM-Explore-4BContext Window=128k, Memory Mechanism=Disabled2026.04 | 40.5 | |
| Mirothinker 8BContext Window=128k, Memory Mechanism=Disabled2026.04 | 40.4 | |
| DeepSeek-V3.2Context Window=128k, Memory Mechanism=Disabled2026.04 | 38.5 | |
| Kimi-ResearcherContext Window=128k, Memory Mechanism=Disabled2026.04 | 36 | |
| Kimi-K2-0905Context Window=128k, Memory Mechanism=Disabled2026.04 | 25.2 |