Swallow - Pre-trained English - OpenBookQA: leaderboard
From the Swallow LLM Leaderboard (Institute of Science Tokyo) pre-trained English board, which evaluates base models without post-training. OpenBookQA four-choice science and commonsense questions, 4-shot; metric is accuracy (random 25%). Upstream publishes 0-1 scores; shown as 0-100, higher is better.
Metric: Accuracy (%). Source: swallow-llm.github.io. Saturation forecast: Estimated already saturated. 50 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B | 45 | #588 |
| 2 | Llama 4 Scout Base | 43.2 | #708 |
| 3 | Qwen 2.5 72B | 41.6 | #512 |
| 4 | Qwen3-14B-Base | 41.6 | #628 |
| 5 | gemma-3-27B-pt | 41.4 | #505 |
| 6 | Qwen3-30B-A3B-Base | 41.4 | #597 |
| 7 | Gemma 2 27B | 41.2 | #803 |
| 8 | Qwen 2.5 14B | 41.2 | #716 |
| 9 | Qwen 2.5 32B | 40.6 | #544 |
| 10 | gemma-3-12B-pt | 39.8 | #686 |
| 11 | Qwen 2.5 7B | 39.2 | #895 |
| 12 | sarashina2-70B | 38.8 | #586 |
| 13 | Gemma 2 9B | 38.2 | #924 |
| 14 | Qwen3-8B-Base | 38.2 | #626 |
| 15 | Qwen3-4B-Base | 38.2 | #880 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=swallow-pre-trained-english-openbookqa · How It Works · Data refreshed daily, snapshot 2026-11-05.