AbstentionBench - false premise - QAQA - F1: leaderboard
Metric: Abstention F1 (%). Source: github.com. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 | 74.13 |
| 2 | GPT-4o | 68.14 |
| 3 | Gemini 1.5 Pro | 67.51 |
| 4 | Llama-3.1-Tulu-3-70B | 66.39 |
| 5 | Llama-3.1-Tulu-3-70B-DPO | 63.81 |
| 6 | Llama 3.1 405B Instruct | 63 |
| 7 | Qwen 2.5 32B Instruct | 59.46 |
| 8 | Llama-3.1-Tulu-3-8B-DPO | 59.18 |
| 9 | Mistral 7B Instruct (v0.3) | 57.6 |
| 10 | Llama 3.3 70B Instruct | 55.4 |
| 11 | Llama-3.1-Tulu-3-8B | 54.75 |
| 12 | Llama 3.1 70B Instruct | 54.55 |
| 13 | Llama 3.1 8B Instruct | 53.39 |
| 14 | Llama-3.1-Tulu-3-8B-SFT | 47.8 |
| 15 | DeepSeek R1 Distill Llama 70B | 47.52 |
Interactive version: theaggregate.ai/benchmark?slug=abstentionbench-false-premise-qaqa-f1 · How It Works · Data refreshed daily, snapshot 2026-09-19.