TimeLitmus - Finance Event-Side Counterfactual Pairs: leaderboard
Metric: Counterfactual pair correctness (%; both independently evaluated endpoints correct on 80 Finance pairs whose event attribute is changed while the series is kept; ten LLMs with deterministic decoding where available, invalid or unparsable outputs scored incorrect). Source: arxiv.org. Saturation forecast: Around 2034. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen Plus | 61.3 |
| 2 | Claude Sonnet 4.6 | 50 |
| 3 | Qwen 3.5 9B | 38.8 |
| 4 | Gemini 3.5 Flash | 37.5 |
| 5 | MiniMax-M3 | 25 |
| 6 | DeepSeek R1 0528 | 18.8 |
| 7 | DeepSeek V4 Flash | 17.5 |
| 8 | GLM-5 | 16.2 |
| 9 | Qwen 3.5 4B | 13.8 |
| 10 | GPT-5.4 | 5 |
Interactive version: theaggregate.ai/benchmark?slug=timelitmus-finance-event-side-counterfactual-pairs · How It Works · Data refreshed daily, snapshot 2026-09-26.