# Best AI for Financial trading and portfolios (November 2026)

The leader on each benchmark in this use case, never combined. Data refreshed 2 Nov 2026.

## Picks

- StockBench: Qwen3-235B-Think: 2.5 final return % (Paper Table 2, 2 Mar 2026), https://benchmarks.finance/leaderboards/stockbench/
- Agent Market Arena (AMA): InvestorAgent / GPT-4.1: 40.8 cumulative return % (TSLA) (Paper Table 1, 30 Oct 2025), https://benchmarks.finance/leaderboards/agent-market-arena/
- InvestorBench: Qwen2.5-72B-Instruct: 46.2 cumulative return % (Paper Table 2, 24 Dec 2024), https://benchmarks.finance/leaderboards/investorbench/
- KTD-Fin: Qwen3.6-Plus: 85.3 total return % (Paper Table 4, 27 May 2026), https://benchmarks.finance/leaderboards/ktd-fin/
- LiveTradeBench: GPT-4.1: 6.3 cumulative return % (Paper Table 2, 5 Nov 2025), https://benchmarks.finance/leaderboards/livetradebench/
- PortBench: GLM-5.1: 0.384 CEPS (0-1) (Paper Table 2, 9 Oct 2026), https://benchmarks.finance/leaderboards/portbench/
- PolyBench: MiMo-V2-Flash: 17.6 Confidence-Weighted Return (CWR) % (Paper Table 5, 3 Apr 2026), https://benchmarks.finance/leaderboards/polybench/
- AI-Trader: MiniMax-M2: 9.6 cumulative return % (Paper Table 1, 1 Dec 2025), https://benchmarks.finance/leaderboards/ai-trader/
- Moneda PortfolioBench: Numa 1: 96 Portfolio tasks, % correct (Moneda run, 2026-11-01, 1 Nov 2026), https://benchmarks.finance/leaderboards/moneda-portfoliobench/

## StockBench: final return % (higher is better, 11 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Qwen3-235B-Think | Qwen | 2.5 | final return % | composite rank 4 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 2 | Qwen3-235B-Ins | Qwen | 2.4 | final return % | composite rank 2 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 3 | GLM-4.5 | Zhipu AI | 2.3 | final return % | composite rank 3 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 4 | Claude-4-Sonnet | Anthropic | 2.2 | final return % | composite rank 7 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 5 | Qwen3-30B-Think | Qwen | 2.1 | final return % | composite rank 6 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 6 | Kimi k2 | Moonshot AI | 1.9 | final return % | composite rank 1 (z-score of return, drawdown, Sortino); avg of 3 runs | Reported by the authors | Paper Table 2 (same as project leaderboard) | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 6 | OpenAI-O3 | OpenAI | 1.9 | final return % | composite rank 5 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 8 | DeepSeek V3.1 | DeepSeek | 1.1 | final return % | composite rank 8 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 9 | gpt-5 | OpenAI | 0.300 | final return % | composite rank 9 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 10 | DeepSeek-V3 | DeepSeek | 0.200 | final return % | composite rank 11 (passive baseline is rank 12 at +0.4%) | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |
| 10 | Qwen3-Coder | Qwen | 0.200 | final return % | composite rank 10 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2510.02209v2 | 2 Mar 2026 |

## Agent Market Arena (AMA): cumulative return % (TSLA) (higher is better, 10 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | InvestorAgent / GPT-4.1 | Not stated | 40.8 | cumulative return % (TSLA) | live 2025-08-01 to 2025-09-30, TSLA; buy-and-hold 46.88 | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 2 | InvestorAgent / GPT-4o | Not stated | 33.0 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 3 | InvestorAgent / Vote | Not stated | 29.1 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 4 | InvestorAgent / Claude-sonnet-4 | Not stated | 28.9 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 5 | TradeAgent / Gemini-2.0-flash | Not stated | 21.9 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 6 | DeepFundAgent / GPT-4o | Not stated | 13.9 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 7 | InvestorAgent / Claude-3.5-haiku | Not stated | 11.6 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 8 | InvestorAgent / Gemini-2.0-flash | Not stated | 10.6 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 9 | DeepFundAgent / Vote | Not stated | 8.6 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |
| 10 | TradeAgent / Vote | Not stated | -0.360 | cumulative return % (TSLA) | live, TSLA | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2510.11695v2 | 30 Oct 2025 |

## InvestorBench: cumulative return % (higher is better, 10 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Qwen2.5-72B-Instruct | Qwen | 46.2 | cumulative return % | stock task, average over 7 stocks, 2020-10-01 to 2021-05-06; buy-and-hold 34.099 | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 2 | GPT-4 | OpenAI | 43.7 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 3 | GPT-4o | OpenAI | 39.0 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 4 | Llama-3.1-70B-Instruct | Meta | 38.9 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 5 | Yi-1.5-34B-Chat | Not stated | 38.0 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 6 | Qwen-2.5-Instruct-7B | Qwen | 29.5 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 7 | DeepSeek-V2-Lite (15.7B) | DeepSeek | 28.7 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 8 | DeepSeek-67B-Chat | DeepSeek | 26.9 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 9 | Llama-3.1-8B-Instruct | Meta | 25.5 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |
| 10 | GPT-o1-preview | OpenAI | 25.1 | cumulative return % | stock task, 7-stock average | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2412.18174v1 | 24 Dec 2024 |

## KTD-Fin: total return % (higher is better, 10 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Qwen3.6-Plus | Qwen | 85.3 | total return % | blinded x open-research, 2024-01-01 to 2026-04-10; alpha rank 2; CSI300 buy-and-hold +36.92 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 2 | GPT 5.5 | OpenAI | 61.3 | total return % | blinded x open-research; alpha rank 6 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 3 | doubao-seed-2.0 | ByteDance | 61.0 | total return % | blinded x open-research; alpha rank 3 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 4 | claude-opus-4-7 | Anthropic | 58.8 | total return % | blinded x open-research; alpha rank 1 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 5 | minimax-m2.7 | MiniMax | 56.3 | total return % | blinded x open-research; alpha rank 4 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 6 | step-3.5-flash | StepFun | 21.9 | total return % | blinded x open-research; alpha rank 5 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 7 | gemini-3.1-pro | Google | 8.3 | total return % | blinded x open-research; alpha rank 7 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 8 | deepseek-v4-pro | DeepSeek | 1.4 | total return % | blinded x open-research; alpha rank 8 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 9 | GLM-5.1 | Zhipu AI | -3.5 | total return % | blinded x open-research; alpha rank 9 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |
| 10 | Kimi K2.6 | Moonshot AI | -24.2 | total return % | blinded x open-research; alpha rank 10 | Reported by the authors | Paper Table 4 | https://arxiv.org/html/2605.28359v1 | 27 May 2026 |

## LiveTradeBench: cumulative return % (higher is better, 10 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | GPT-4.1 | OpenAI | 6.3 | cumulative return % | US stock market, live 2025-08-18 to 2025-10-24 (50 trading days) | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 2 | GPT-o3 | OpenAI | 6.0 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 3 | gpt-5 | OpenAI | 5.3 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 4 | Qwen2.5-72B-Instruct | Qwen | 5.2 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 5 | Llama4-Scout | Meta | 4.7 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 6 | Llama4-Maverick | Meta | 4.5 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 7 | grok-4 | xAI | 4.3 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 8 | Claude Opus 4 | Anthropic | 3.9 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 9 | Claude Opus 4.1 | Anthropic | 3.7 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |
| 10 | Claude-Sonnet-3.7 | Anthropic | 3.6 | cumulative return % | US stock market, live | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2511.03628v1 | 5 Nov 2025 |

## PortBench: CEPS (0-1) (higher is better, 10 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | GLM-5.1 | Zhipu AI | 0.384 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 2 | Qwen3.6-Plus | Qwen | 0.300 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 3 | Qwen3.7-Max | Qwen | 0.292 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 4 | Kimi K2.6 | Moonshot AI | 0.274 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 5 | Qwen3.6-35B-A3B | Qwen | 0.272 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 6 | DS-V4-Pro | DeepSeek | 0.266 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 7 | DB-2.0-Pro | Not stated | 0.263 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 8 | HY3-Preview | Tencent | 0.258 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 9 | DB-2.0-Lite | Not stated | 0.244 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |
| 10 | DS-V4-Flash | DeepSeek | 0.226 | CEPS (0-1) | pipeline, balanced risk profile | Reported by the authors | Paper Table 2 | https://arxiv.org/html/2605.27887v6 | 9 Oct 2026 |

## PolyBench: Confidence-Weighted Return (CWR) % (higher is better, 7 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | MiMo-V2-Flash | Xiaomi | 17.6 | Confidence-Weighted Return (CWR) % | base lot $10, 2026-02-06 to 2026-02-12 | Reported by the authors | Paper Table 5 | https://arxiv.org/html/2604.14199v1 | 3 Apr 2026 |
| 2 | Gemini-3-Flash | Google | 6.2 | Confidence-Weighted Return (CWR) % | base lot $10 | Reported by the authors | Paper Table 5 | https://arxiv.org/html/2604.14199v1 | 3 Apr 2026 |
| 3 | Trinity-Large | Not stated | -9.2 | Confidence-Weighted Return (CWR) % | base lot $10 | Reported by the authors | Paper Table 5 | https://arxiv.org/html/2604.14199v1 | 3 Apr 2026 |
| 4 | deepseek-v3.2 | DeepSeek | -11.4 | Confidence-Weighted Return (CWR) % | base lot $10 | Reported by the authors | Paper Table 5 | https://arxiv.org/html/2604.14199v1 | 3 Apr 2026 |
| 5 | Grok-4.1-Fast | xAI | -12.1 | Confidence-Weighted Return (CWR) % | base lot $10 | Reported by the authors | Paper Table 5 | https://arxiv.org/html/2604.14199v1 | 3 Apr 2026 |
| 6 | GPT-OSS 120B | OpenAI | -17.8 | Confidence-Weighted Return (CWR) % | base lot $10 | Reported by the authors | Paper Table 5 | https://arxiv.org/html/2604.14199v1 | 3 Apr 2026 |
| 7 | MiniMax-M2.5 | MiniMax | -25.2 | Confidence-Weighted Return (CWR) % | base lot $10 | Reported by the authors | Paper Table 5 | https://arxiv.org/html/2604.14199v1 | 3 Apr 2026 |

## AI-Trader: cumulative return % (higher is better, 6 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | MiniMax-M2 | MiniMax | 9.6 | cumulative return % | US market (Nasdaq-100, hourly), 2025-10-01 to 2025-11-07; QQQ baseline 1.87 | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2512.10971v1 | 1 Dec 2025 |
| 2 | DeepSeek V3.1 | DeepSeek | 8.4 | cumulative return % | US market, hourly | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2512.10971v1 | 1 Dec 2025 |
| 3 | Claude-3.7-Sonnet | Anthropic | 3.1 | cumulative return % | US market, hourly | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2512.10971v1 | 1 Dec 2025 |
| 4 | gpt-5 | OpenAI | 1.6 | cumulative return % | US market, hourly | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2512.10971v1 | 1 Dec 2025 |
| 5 | Qwen3-Max | Qwen | 0.390 | cumulative return % | US market, hourly | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2512.10971v1 | 1 Dec 2025 |
| 6 | Gemini 2.5 Flash | Google | -0.060 | cumulative return % | US market, hourly | Reported by the authors | Paper Table 1 | https://arxiv.org/html/2512.10971v1 | 1 Dec 2025 |

## Moneda PortfolioBench: Portfolio tasks, % correct (higher is better, 1 models)

| Rank | Model | Maker | Score | Metric | Setting | Reported by | Source | URL | Date |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Numa 1 | Moneda | 96 | Portfolio tasks, % correct | Portfolio tasks only (150; forecasts and mandate funds not yet run); graded by code | Run by Moneda | Moneda run, 2026-11-01 | https://benchmarks.finance/method/ | 1 Nov 2026 |

## Also in this use case (no dated scores yet)

- Alpha Arena (Nof1): https://benchmarks.finance/benchmarks/alpha-arena/
- Market-Bench (AfterQuery): https://benchmarks.finance/benchmarks/afterquery-market-bench/

Source: https://benchmarks.finance/best/trading-and-portfolios/

Created and maintained by Moneda.