TimeLitmus - Finance Natural Prediction: leaderboard
Metric: Natural accuracy (%; 380 Finance records of FNSPID market events with four expected-response classes (strong or weak, up or down); ten LLMs with deterministic decoding where available, invalid or unparsable outputs scored incorrect). Source: arxiv.org. Saturation forecast: Around 2033. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5 | 51.3 |
| 2 | DeepSeek V4 Flash | 48.7 |
| 3 | MiniMax-M3 | 47.1 |
| 4 | GPT-5.4 | 44.7 |
| 5 | DeepSeek R1 0528 | 44.5 |
| 6 | Gemini 3.5 Flash | 42.1 |
| 7 | Qwen Plus | 41.1 |
| 8 | Qwen 3.5 4B | 40.8 |
| 9 | Qwen 3.5 9B | 40.3 |
| 10 | Claude Sonnet 4.6 | 37.1 |
Interactive version: theaggregate.ai/benchmark?slug=timelitmus-finance-natural-prediction · How It Works · Data refreshed daily, snapshot 2026-09-26.