SimpleBench
Trick questions about everyday physical and social situations that people find easy. Read directly from the SimpleBench leaderboard, so new models appear before the Epoch copy; both share one weight.
| Category | Reasoning |
|---|---|
| Metric | Score (%), 5 runs |
| Source | SimpleBench (original) |
| License | None stated |
| Benchmark page | simple-bench.com |
| Status | Scored |
| Weight | 1.0 within Reasoning |
| Fit | Discrimination 0.83, noise 0.37 |
| Lineage | Shares weight with simplebench |
Results
| # | Model | Provider | Result | Date |
|---|---|---|---|---|
| 1 | Claude Fable 5.2 | Anthropic | 94.9% | 2026-11-10 |
| 2 | Gemini 4 Carbon | 92.6% | 2026-11-10 | |
| 3 | Gemini 4 Argon | 91.7% | 2026-11-10 | |
| 4 | Claude Opus 5.5 | Anthropic | 88.4% | 2026-09-24 |
| 5 | Claude Fable 5.1 | Anthropic | 86.6% | 2026-09-03 |
| 6 | GPT-6 Astra Pro | OpenAI | 86.5% | 2026-09-07 |
| 7 | GPT-6 Astra | OpenAI | 83.6% | 2026-09-07 |
| 8 | GPT-6.1 Sol | OpenAI | 82.9% | 2026-10-01 |
| 9 | Gemini 3.8 Flash | 82.4% | 2026-09-03 | |
| 10 | Claude Fable 5 | Anthropic | 81.9% | 2026-06-10 |
| 11 | Muse Spark 1.3 | Meta | 81.8% | 2026-09-03 |
| 12 | Claude Opus 5 | Anthropic | 80.6% | 2026-07-24 |
| 13 | Gemini 3.1 Pro Preview | 79.6% | 2026-02-17 | |
| 14 | GPT-5.5 Pro | OpenAI | 76.9% | 2026-04-24 |
| 15 | Gemini 3.5 Flash | 76.7% | 2026-05-20 | |
| 16 | Gemini 3 Pro Preview | 76.4% | 2025-11-18 | |
| 17 | Grok 4.6 | xAI | 75.9% | 2026-08-13 |
| 18 | Claude Sonnet 5.5 | Anthropic | 75.9% | 2026-10-01 |
| 19 | Muse Spark 1.2 | Meta | 74.5% | 2026-08-13 |
| 20 | GPT-6 Sol | OpenAI | 73.1% | 2026-09-24 |
| 21 | Muse Ember | Meta | 72.7% | 2026-11-10 |
| 22 | GPT-6.1 Terra | OpenAI | 72.2% | 2026-11-10 |
| 23 | GPT-5.6 Sol Pro Extra High | OpenAI | 71.7% | 2026-07-09 |
| 24 | Qwen3.7 Max | Alibaba | 70.4% | 2026-05-22 |
| 25 | Grok 4.5 | xAI | 70.0% | 2026-07-08 |
| 26 | GPT-5.5 | OpenAI | 69.0% | 2026-04-24 |
| 27 | Claude Opus 4.6 | Anthropic | 67.6% | 2026-02-17 |
| 28 | DeepSeek V4.1 Flash | DeepSeek | 66.7% | 2026-09-12 |
| 29 | GLM-5.3 | Zhipu AI | 66.2% | 2026-08-19 |
| 30 | Claude Opus 4.8 | Anthropic | 64.8% | 2026-05-29 |
| 31 | GPT-5.6 Sol Extra High | OpenAI | 64.8% | 2026-07-09 |
| 32 | Qwen3.6 Max Preview | Alibaba | 63.0% | 2026-05-20 |
| 33 | Qwen3.8 2.4T A95B | Alibaba | 62.5% | 2026-08-13 |
| 34 | Gemini 2.5 Pro | 62.4% | 2026-11-11 | |
| 35 | Claude Opus 4.5 | Anthropic | 62.0% | 2025-11-20 |
| 36 | Claude Opus 4.7 | Anthropic | 61.7% | 2026-04-22 |
| 37 | GPT-5 Pro | OpenAI | 61.6% | 2025-10-22 |
| 38 | DeepSeek V4 Flash | DeepSeek | 61.1% | 2026-08-03 |
| 39 | Gemini 3 Flash Preview | 61.1% | 2025-12-19 | |
| 40 | Kimi K3 Max | Moonshot AI | 60.7% | 2026-07-17 |
| 41 | Claude Sonnet 5 | Anthropic | 60.6% | 2026-07-09 |
| 42 | Grok 4 | xAI | 60.5% | 2026-11-11 |
| 43 | Qwen3.8 27B | Alibaba | 60.2% | 2026-08-20 |
| 44 | Claude Opus 4.1 | Anthropic | 60.0% | 2026-11-11 |
| 45 | Claude Opus 4 | Anthropic | 58.8% | 2026-11-11 |
| 46 | GLM-5.2 | Zhipu AI | 58.8% | 2026-06-17 |
| 47 | Kimi K2.7 Code | Moonshot AI | 57.9% | 2026-07-09 |
| 48 | GPT-5.2 Pro Extra High | OpenAI | 57.4% | 2025-12-12 |
| 49 | GPT-5 High | OpenAI | 56.7% | 2026-11-11 |
| 50 | Grok 4.1 Fast | xAI | 56.0% | 2025-11-20 |
| 51 | GLM-5.1 | Zhipu AI | 55.1% | 2026-07-09 |
| 52 | Claude Sonnet 4.5 | Anthropic | 54.3% | 2026-11-11 |
| 53 | GLM-5 | Zhipu AI | 53.2% | 2026-02-17 |
| 54 | GPT-5.1 High | OpenAI | 53.2% | 2025-11-16 |
| 55 | o3 High | OpenAI | 53.1% | 2026-11-11 |
| 56 | DeepSeek V4 Pro | DeepSeek | 50.9% | 2026-06-02 |
| 57 | Inkling | Thinking Machines | 50.0% | 2026-07-22 |
| 58 | GPT-5.6 Terra Extra High | OpenAI | 48.9% | 2026-07-09 |
| 59 | GLM-4.7 | Zhipu AI | 47.7% | 2025-12-23 |
| 60 | Kimi K2.5 | Moonshot AI | 46.8% | 2026-02-17 |
| 61 | GPT-5.6 Luna Extra High | OpenAI | 46.8% | 2026-07-09 |
| 62 | Claude Sonnet 3.7 Thinking | Anthropic | 46.4% | 2026-11-11 |
| 63 | MiniMax-M3 | MiniMax | 45.8% | 2026-07-09 |
| 64 | GPT-5.2 High | OpenAI | 45.8% | 2025-12-12 |
| 65 | Claude Sonnet 4 Thinking | Anthropic | 45.5% | 2026-11-11 |
| 66 | Claude Sonnet 3.7 | Anthropic | 44.9% | 2026-11-11 |
| 67 | Nemotron 3 Ultra | NVIDIA | 41.7% | 2026-06-07 |
| 68 | o1-preview | OpenAI | 41.7% | 2026-11-11 |
| 69 | Claude 3.5 Sonnet | Anthropic | 41.4% | 2026-11-11 |
| 70 | Gemini 2.5 Flash | 41.2% | 2025-10-22 | |
| 71 | DeepSeek-R1 | DeepSeek | 40.8% | 2026-11-11 |
| 72 | o1 High | OpenAI | 40.1% | 2026-11-11 |
| 73 | DeepSeek V3.1 | DeepSeek | 40.0% | 2026-11-11 |
| 74 | Kimi K2 Thinking | Moonshot AI | 39.6% | 2025-11-07 |
| 75 | o4-mini High | OpenAI | 38.7% | 2026-11-11 |
| 76 | o1 Medium | OpenAI | 36.7% | 2026-11-11 |
| 77 | Grok 3 | xAI | 36.1% | 2026-11-11 |
| 78 | Qwen3.6 Flash | Alibaba | 35.2% | 2026-07-10 |
| 79 | MiniMax-M2.1 | MiniMax | 34.7% | 2025-12-23 |
| 80 | GPT-4.5 | OpenAI | 34.5% | 2026-11-11 |
| 81 | Gemini 2.0 Flash (Dec 2024) | 31.1% | 2026-11-11 | |
| 82 | Qwen3 235B-A22B | Alibaba | 31.0% | 2026-11-11 |
| 83 | Gemini 2.0 Flash Thinking | 30.7% | 2026-11-11 | |
| 84 | Llama 4 Maverick | Meta | 27.7% | 2026-11-11 |
| 85 | DeepSeek-V3 | DeepSeek | 27.2% | 2026-11-11 |
| 86 | Gemini 1.5 Pro (Sept 2024) | 27.1% | 2026-11-11 | |
| 87 | GPT-4.1 | OpenAI | 27.0% | 2026-11-11 |
| 88 | Kimi K2 0711 | Moonshot AI | 26.3% | 2026-11-11 |
| 89 | GPT-4 Turbo | OpenAI | 25.1% | 2026-11-11 |
| 90 | MiniMax-M2 | MiniMax | 25.0% | 2025-11-19 |
| 91 | Claude 3 Opus | Anthropic | 23.5% | 2026-11-11 |
| 92 | Llama 3.1-405B | Meta | 23.0% | 2026-11-11 |
| 93 | o3-mini High | OpenAI | 22.8% | 2026-11-11 |
| 94 | GPT OSS 120B | OpenAI | 22.1% | 2026-11-11 |
| 95 | Mistral Large 3 | Mistral | 20.4% | 2025-12-04 |
| 96 | Llama-3.3-70B-Instruct | Meta | 19.9% | 2026-11-11 |
| 97 | o1-mini | OpenAI | 18.1% | 2026-11-11 |
| 98 | GPT-4o | OpenAI | 17.8% | 2026-11-11 |
| 99 | Command R+ | Cohere | 17.4% | 2026-11-11 |
| 100 | GPT-4o mini | OpenAI | 10.7% | 2026-11-11 |
| 101 | GPT-3.5-turbo | OpenAI | 8.0% | 2026-11-11 |