QuantArena - One-shot - Sealed Period: leaderboard
QuantArena One-shot: 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 Version-fixed quality/diversity composite scaled0-100; out-of-sample combination unpublished.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 2032. 38 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Medium) | 40.65 | #4 (Claude Opus 5.5) |
| 2 | GPT-5.6 Terra (Non-reasoning) | 40.25 | #40 (GPT-5.6 Terra) |
| 3 | GPT-5.6 Terra (High) | 39.64 | #40 (GPT-5.6 Terra) |
| 4 | Claude Opus 5.5 (Max) | 38.69 | #4 (Claude Opus 5.5) |
| 5 | Claude Sonnet 5.5 (High) | 38.5 | #11 (Claude Sonnet 5.5) |
| 6 | Gemini 3.8 Flash (Medium) | 36.04 | #23 (Gemini 3.8 Flash) |
| 7 | Claude Sonnet 5.5 (Low) | 35.76 | #11 (Claude Sonnet 5.5) |
| 8 | Claude Opus 5.5 (xHigh) | 34.88 | #4 (Claude Opus 5.5) |
| 9 | Claude Opus 5.5 (High) | 34.52 | #4 (Claude Opus 5.5) |
| 10 | GPT-6 Astra (High) | 33.92 | #6 (GPT-6 Astra) |
| 11 | Claude Sonnet 5.5 (xHigh) | 32.4 | #11 (Claude Sonnet 5.5) |
| 12 | Gemini 3.8 Flash (High) | 32.11 | #23 (Gemini 3.8 Flash) |
| 13 | GLM-5.3 (High) | 31.79 | #36 (GLM-5.3) |
| 14 | Claude Opus 5.5 (Low) | 31.53 | #4 (Claude Opus 5.5) |
| 15 | Claude Sonnet 5.5 (Max) | 30.77 | #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-one-shot-sealed-period · How It Works · Data refreshed daily, snapshot 2026-10-23.