DoubtLess Evaluation - AIME25 and AMC23 - Plain: leaderboard
DoubtLess Evaluation - AIME25 and AMC23 - Plain. 70 problems,three seeds per problem; combined accuracy. Plain decoding; DoubtLess uses matched small thinker from same family at source default strength. Metric: Accuracy (%). Primary published table; source configurations remain distinct.
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around January 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Granite 4.2 30B | 89 | #405 |
| 2 | Qwen 3 32B | 86.2 | #436 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=doubtless-evaluation-aime25-and-amc23-plain · How It Works · Data refreshed daily, snapshot 2026-10-16.