ParliamentBench: leaderboard
Metric: Overall (%). Source: arxiv.org. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 81 |
| 2 | Kimi K2.5 | 76 |
| 3 | Grok 4.1 Fast | 69 |
| 4 | DeepSeek V3.1 Terminus | 66 |
| 5 | Llama 3.3 70B | 58 |
| 6 | Qwen 3.5 397B A17B | 56 |
| 7 | GPT-OSS-120B | 50 |
| 8 | DeepSeek R1 | 46 |
| 9 | Llama 3.1 70B | 42 |
| 10 | Gemma 3 27B | 39 |
| 11 | GPT-OSS-20B | 24 |
Interactive version: theaggregate.ai/benchmark?slug=parliamentbench · How It Works · Data refreshed daily, snapshot 2026-09-05.