QuantArena - Iterative - Sealed Period: leaderboard
QuantArena Iterative: shared equity research environment,2022-2023 research and sealed 2024 out-of-sample windows. Version-fixed quality/diversity composite scaled0-100; out-of-sample combination unpublished. Each of 38 requested effort configurations retained; no best-effort pooling. These evaluate agent-generated strategies, not investment advice or model response speed. Score (%).
Metric: Score (%). Source: arxiv.org. Saturation forecast: Around 2030. 38 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Sol (Medium) | 52.23 | #15 (GPT-6 Sol) |
| 2 | GPT-6 Astra (xHigh) | 50.16 | #6 (GPT-6 Astra) |
| 3 | GPT-6 Astra (Max) | 49.64 | #6 (GPT-6 Astra) |
| 4 | GPT-6 Sol (xHigh) | 49.26 | #15 (GPT-6 Sol) |
| 5 | GPT-6 Astra (Medium) | 46.78 | #6 (GPT-6 Astra) |
| 6 | GPT-5.6 Terra (Max) | 46.39 | #40 (GPT-5.6 Terra) |
| 7 | GPT-6 Sol (Max) | 44.81 | #15 (GPT-6 Sol) |
| 8 | GPT-6 Astra (Low) | 42.56 | #6 (GPT-6 Astra) |
| 9 | GPT-5.6 Terra (xHigh) | 42.28 | #40 (GPT-5.6 Terra) |
| 10 | GPT-5.6 Terra (High) | 40.17 | #40 (GPT-5.6 Terra) |
| 11 | GPT-6 Astra (High) | 39.99 | #6 (GPT-6 Astra) |
| 12 | GPT-6 Sol (High) | 38.92 | #15 (GPT-6 Sol) |
| 13 | Claude Opus 5.5 (Medium) | 38.92 | #4 (Claude Opus 5.5) |
| 14 | Gemini 3.8 Flash (Medium) | 38.52 | #23 (Gemini 3.8 Flash) |
| 15 | Claude Sonnet 5.5 (xHigh) | 38.13 | #11 (Claude Sonnet 5.5) |
No result here: #7 GPT-6.1 Sol, #8 Gemini 4 Argon, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=quantarena-iterative-sealed-period · How It Works · Data refreshed daily, snapshot 2026-10-23.