Agent Evaluation on FutureX May W2, 56 events
5RankH2O AI Super Agent v1.82
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| H2O AI Super Agent v1.82Model=Claude-Sonnet-4.62026.06 | 5 | 100 | 43.57 | 41.78 | 38.31 | 46.57 | |
| FutureGPTv1Model=GPT-5.42026.06 | 6 | 87.5 | 57.14 | 37.78 | 37.12 | 46.36 | |
| GPT-5.4-SC@3 (GPT@3)Model=GPT-5.42026.06 | 7 | 87.5 | 57.14 | 37.77 | 34.45 | 45.29 | |
| GPT-5.4 w/ search (GPT-search)Model=GPT-5.42026.06 | 8 | 75 | 50 | 39.55 | 34.45 | 43.15 | |
| GPT-5.4-SC@5 (GPT@5)Model=GPT-5.42026.06 | 9 | 75 | 50 | 36 | 34.45 | 42.08 | |
| Kimi-K2.5 (Simple ReAct)Model=Kimi-K2.52026.06 | 17 | 87.5 | 42.14 | 29.24 | 30.82 | 38.28 |