Leaderboard, made by Mostapha Benhenda
IPO Finance Agent
IPO due-diligence questions on recent S-1 filings, answered by a tool-using agent with web search and EDGAR access (forked from Vals AI's Finance Agent v2 harness).
IPO Finance Agent arXiv v3 (2026-06-30)
mean rubric score %, higher is better. 6 models.
Updated 30 Jun 2026
- GLM-5.279.8
- GLM-5.179.7
- Qwen3.7-Max78.9
- MiMo-2.5 Pro77.2
- Kimi K2.668
- Nemotron 3 Ultra45.5
IPO Finance Agent arXiv v3 (2026-06-30)
mean rubric score %, higher is better. 6 models.
Updated 30 Jun 2026
- 1GLM-5.279.8
- 2GLM-5.179.7
- 3Qwen3.7-Max78.9
- 4MiMo-2.5 Pro77.2
- 5Kimi K2.668
- 6Nemotron 3 Ultra45.5
| 1 | GLM-5.2 | Zhipu AI | 79.8 | public SpaceX set (n=70), agent harness | Paper Table 1 Reported by the authors, reported 30 Jun 2026 · checked 1 Nov 2026 |
|---|---|---|---|---|---|
| 2 | GLM-5.1 | Zhipu AI | 79.7 | public SpaceX set (n=70), agent harness | Paper Table 1 Reported by the authors, reported 30 Jun 2026 · checked 1 Nov 2026 |
| 3 | Qwen3.7-Max | Qwen | 78.9 | public SpaceX set (n=70), agent harness | Paper Table 1 Reported by the authors, reported 30 Jun 2026 · checked 1 Nov 2026 |
| 4 | MiMo-2.5 Pro | Xiaomi | 77.2 | public SpaceX set (n=70), agent harness | Paper Table 1 Reported by the authors, reported 30 Jun 2026 · checked 1 Nov 2026 |
| 5 | Kimi K2.6 | Moonshot AI | 68 | public SpaceX set (n=70), agent harness | Paper Table 1 Reported by the authors, reported 30 Jun 2026 · checked 1 Nov 2026 |
| 6 | Nemotron 3 Ultra | NVIDIA | 45.5 | public SpaceX set (n=70), agent harness | Paper Table 1 Reported by the authors, reported 30 Jun 2026 · checked 1 Nov 2026 |