PerfReasoning - Default Effort: leaderboard
PerfReasoning both-exact pass rate for models with a single default reasoning setting. Higher is better. Source: arxiv.org/abs/2609.04476.
Metric: Both-Exact Pass Rate (%). Source: arxiv.org. Saturation forecast: Around 2031. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.3 | 3.2 | #98 |
| 2 | GLM-5.1 | 0 | #109 |
| 3 | MiniMax-M3 | 0 | #151 |
| 4 | GLM-5.2 | 0 | #79 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=perfreasoning-default-effort · How It Works · Data refreshed daily, snapshot 2026-11-06.