CircuitReason-1k - Long-Horizon Reasoning: leaderboard
The 332 long-horizon problems of CircuitReason-1k (2026), grouped by the length of the dependent chain from diagram evidence to the final physical answer. Accuracy in percent, every requested output must be correct; higher is better.
Metric: Accuracy (%; exact problem-level correctness on the 332 long-horizon problems of CircuitReason-1k's authentic textbook circuit problems; typed deterministic scoring for 585 problems and identity-blinded, reference-assisted multi-model judge consensus (strict majority of at least three votes) for the other 415; every requested output must be correct; missing, failed or unresolved answers count as wrong; image and question only, no output-token cap, open models in their native thinking mode). Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.6 | 83.73 | #173 |
| 2 | Qwen 3.5 122B A10B | 82.83 | #329 |
| 3 | Gemini 3.1 Pro (Preview) | 80.42 | #91 |
| 4 | GPT-5.6 Sol | 80.12 | #29 |
| 5 | Claude Sonnet 4.6 | 59.04 | #158 |
| 6 | Qwen 3 VL 235B A22B (Thinking) | 57.53 | #451 |
| 7 | Qwen 3 VL 8B (Thinking) | 40.66 | #887 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=circuitreason-1k-long-horizon-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-12.