Reasoning Benchmarks
Logical reasoning and problem solving - Compare AI models across 2 logical reasoning benchmarks including SimpleQA, MuSR, and more.
Filters & Search
Filter models by creator or search by name to find the perfect AI model for your needs
Reasoning Benchmark Results
Showing 15 of 20 models • Click column headers to sort
SimpleQAFactual question answering benchmark | MuSRComplex multi-step reasoning problems | ||||
|---|---|---|---|---|---|
1 GPT-5 (high) OpenAI | OpenAI | Closed-source | 69 | 86% | 84% |
2 GPT-5 (medium) OpenAI | OpenAI | Closed-source | 68 | 84% | 82% |
3 Grok 4 xAI | xAI | Closed-source | 68 | 82% | 80% |
4 o3-pro OpenAI | OpenAI | Closed-source | 68 | 85% | 83% |
5 o3 OpenAI | OpenAI | Closed-source | 67 | 83% | 81% |
6 o4-mini (high) OpenAI | OpenAI | Closed-source | 65 | 80% | 78% |
7 Gemini 2.5 Pro Google | Closed-source | 65 | 81% | 79% | |
8 GPT-5 mini OpenAI | OpenAI | Closed-source | 64 | 77% | 75% |
9 Claude 4.1 Opus Anthropic | Anthropic | Closed-source | 61 | 74% | 72% |
10 Claude 4 Sonnet Anthropic | Anthropic | Closed-source | 59 | 71% | 69% |
11 Llama 3.1 405B Meta | Meta | Open-source | 58 | 68% | 66% |
12 Mistral Large 2 Mistral | Mistral | Open-source | 57 | 66% | 64% |
13 GPT-4o OpenAI | OpenAI | Closed-source | 56 | 64% | 62% |
14 Claude 3.5 Sonnet Anthropic | Anthropic | Closed-source | 55 | 63% | 61% |
15 Gemini 1.5 Pro Google | Closed-source | 54 | 62% | 60% |
Showing 15 of 20 models
About Reasoning Benchmarks
SimpleQA
Factual question answering benchmark
MuSR
Complex multi-step reasoning problems