FactArena - Justification Soundness: leaderboard
Metric: Elo rating from pairwise judged comparisons. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 (2025-04-16) | 1292.55 |
| 2 | DeepSeek R1 | 1131.83 |
| 3 | O4 Mini (2025-04-16) | 1097.33 |
| 4 | Gemini 2.5 Pro (Preview 06-05) | 1081.98 |
| 5 | GPT-4.5 (Preview) | 1053.24 |
| 6 | GPT-4.1 | 1044.03 |
| 7 | Grok 3 | 1026.05 |
| 8 | Grok 3 Mini Beta | 958.97 |
| 9 | Claude Opus 4 (20250514) | 958.32 |
| 10 | Gemini 2.5 Flash | 956.76 |
| 11 | DeepSeek V3 | 938.83 |
| 12 | Claude Sonnet 4 (20250514) | 919.29 |
| 13 | Llama 4 Maverick Instruct | 916.31 |
| 14 | GPT-4o | 891.96 |
| 15 | Qwen 3 235B A22B | 891.82 |
Interactive version: theaggregate.ai/benchmark?slug=factarena-justification-soundness · How It Works · Data refreshed daily, snapshot 2026-09-25.