SPaRC Inspect 1-A Full Test - Level 3: leaderboard
Solve all 500 spatial pathfinding test puzzles under Inspect task version 1-A at a pinned dataset revision. A path must satisfy every rule. Overall and five difficulty levels are accuracy; invalid paths are errors. Only complete, error-free runs enter this protocol; explicit API identities, reasoning and output limits remain attached.
Metric: Accuracy (%). Source: sparc.gipplab.org. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol (Medium) | 87.6 | #8 (GPT-6.1 Sol) |
| 2 | Qwen 2.5 72B Instruct | 1.7 | #446 |
| 3 | Gemma 3 27B (IT) | 0 | #516 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=sparc-inspect-1-a-full-test-level-3 · How It Works · Data refreshed daily, snapshot 2026-10-16.