TimeLitmus - Finance Hard Paired Contrasts: leaderboard
Metric: Hard paired contrast pair correctness (%; both endpoints correct on 360 naturally occurring similar Finance pairs with different gold responses; 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 | 19.2 |
| 2 | DeepSeek V4 Flash | 16.7 |
| 3 | DeepSeek R1 0528 | 16.1 |
| 4 | Claude Sonnet 4.6 | 15 |
| 5 | MiniMax-M3 | 13.9 |
| 6 | Qwen 3.5 4B | 12.2 |
| 7 | Gemini 3.5 Flash | 9.4 |
| 8 | Qwen Plus | 8.9 |
| 9 | GPT-5.4 | 8.6 |
| 10 | Qwen 3.5 9B | 3.3 |
Interactive version: theaggregate.ai/benchmark?slug=timelitmus-finance-hard-paired-contrasts · How It Works · Data refreshed daily, snapshot 2026-09-26.