HardcoreLogic - Increased Complexity — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 18 models tracked.

Top models

#ModelScore
1GPT-569.89
2Grok 458.26
3GPT-5 Mini55.76
4O4 Mini55.11
5GPT-OSS-120B54.08
6Grok 3 Mini48.48
7Qwen 3 235B A22B (Thinking)46.93
8DeepSeek R1 052845.87
9DeepSeek V3.144.61
10Gemini 2.5 Pro43.8
11Qwen 3 Next 80B A3B (Thinking)41.97
12Seed-OSS-36B-Instruct41.01
13Claude Sonnet 4 (Thinking)34.67
14Qwen 3 32B25.38
15Gemini 2.5 Flash25.11

Interactive version: aibenchmarks.dev/benchmark?slug=hardcorelogic-increased-complexity · How the rankings work · Data refreshed daily, snapshot 2026-07-17.