CircuitReason-1k - Long-Horizon Reasoning: leaderboard

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 December 2026. 9 models tracked.

Top models

#ModelScore
1Kimi K2.683.73
2Qwen 3.5 122B A10B82.83
3Gemini 3.1 Pro (Preview)80.42
4GPT-5.6 Sol80.12
5Claude Sonnet 4.659.04
6Qwen 3 VL 235B A22B (Thinking)57.53
7Qwen 3 VL 8B (Thinking)40.66

Interactive version: theaggregate.ai/benchmark?slug=circuitreason-1k-long-horizon-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-26.