QuantArena - Iterative - Overall: 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 Version-fixed quality/diversity composite scaled0-100; out-of-sample combination unpublished.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 Astra (xHigh) | 51.29 | #6 (GPT-6 Astra) |
| 2 | GPT-6 Sol (xHigh) | 51.14 | #15 (GPT-6 Sol) |
| 3 | GPT-6 Astra (Max) | 50.63 | #6 (GPT-6 Astra) |
| 4 | GPT-6 Sol (Medium) | 49.8 | #15 (GPT-6 Sol) |
| 5 | GPT-5.6 Terra (Max) | 47.58 | #40 (GPT-5.6 Terra) |
| 6 | GPT-6 Astra (Low) | 47.22 | #6 (GPT-6 Astra) |
| 7 | GPT-6 Astra (Medium) | 47.17 | #6 (GPT-6 Astra) |
| 8 | GPT-6 Sol (Max) | 45.31 | #15 (GPT-6 Sol) |
| 9 | GPT-5.6 Terra (xHigh) | 44.77 | #40 (GPT-5.6 Terra) |
| 10 | Claude Opus 5.5 (Medium) | 44.28 | #4 (Claude Opus 5.5) |
| 11 | GPT-6 Astra (High) | 43.7 | #6 (GPT-6 Astra) |
| 12 | Gemini 3.8 Flash (Medium) | 43.04 | #23 (Gemini 3.8 Flash) |
| 13 | GPT-6 Sol (High) | 42.89 | #15 (GPT-6 Sol) |
| 14 | Claude Opus 5.5 (xHigh) | 41.92 | #4 (Claude Opus 5.5) |
| 15 | GPT-5.6 Terra (High) | 41.54 | #40 (GPT-5.6 Terra) |
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-overall · How It Works · Data refreshed daily, snapshot 2026-10-23.