LLM2014 Logic 2026-02: leaderboard
LLM2014 monthly logic benchmark for 2026-02, reporting aggregate logical-reasoning performance on the source score scale.
Metric: Median Score. Source: raw.githubusercontent.com. Saturation forecast: Around January 2027. 46 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (Thinking) | 78.02 | #63 (Claude Opus 4.6) |
| 2 | GPT-5.2 (High) | 76.82 | #110 (GPT-5.2) |
| 3 | Gemini 3.1 Pro (Preview) | 75.02 | #58 |
| 4 | Seed 2.0 Pro (High) | 69.55 | #118 (Seed 2.0 Pro) |
| 5 | Gemini 3 Pro | 68.14 | #80 |
| 6 | GPT-5 Mini (High) | 67.84 | #186 (GPT-5 Mini) |
| 7 | Gemini 3 Flash (High) | 66.09 | #99 (Gemini 3 Flash) |
| 8 | Kimi K2.5 (Thinking) | 60.75 | #144 (Kimi K2.5) |
| 9 | Grok 4 | 58.51 | #181 |
| 10 | GLM-5 (Thinking) | 55.87 | #141 (GLM-5) |
| 11 | Qwen 3.5 Plus (Thinking) | 53.8 | #125 (Qwen 3.5 Plus) |
| 12 | Claude Sonnet 4.5 (Thinking) | 52.81 | #142 (Claude Sonnet 4.5) |
| 13 | Claude Opus 4.6 | 51.55 | #63 |
| 14 | Qwen 3.5 27B (Thinking) | 50.24 | #187 (Qwen 3.5 27B) |
| 15 | MiniMax-M2.5 | 49.36 | #303 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2026-02 · How It Works · Data refreshed daily, snapshot 2026-10-20.