MMLU Pro - Computer Science
General QA · 2024-06-03
The Computer Science split of MMLU Pro. Its guessing floor averages the reciprocal option count across all 410 subject questions in official dataset revision b189ec765aa7ed75c8acfea42df31fdae71f97be. This component remains distinct from the parent aggregate.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5.1 | 94.9 |
| Opus 4.7 | 92.7 |
| Opus 4.8 | 92.7 |
| Gemini 3.1 Pro Preview | 92.7 |
| Gemini 3.8 Flash | 92.7 |
| Gemini 3.7 Flash | 92.0 |
| Gemini 3.5 Flash | 91.7 |
| Gemini 3.6 Flash | 91.7 |
| Grok 4.6 | 91.7 |
| Gemini 3 Pro Preview | 91.5 |
| Kimi K2.6 | 91.2 |
| Kimi K3 | 91.2 |
| Qwen3.7-Max (source unspecified) | 91.2 |
| Gemini 3 Flash Preview | 91.0 |
| GPT-5.6 Terra | 91.0 |
| Grok 4.5 | 91.0 |
| Qwen3.5 Plus (2026-02-15) | 91.0 |
| Qwen3.8-Max | 91.0 |
| Opus 4.6 | 90.7 |
| GPT-5.6 Sol | 90.7 |
| Muse Spark 1.1 | 90.7 |
| Muse Spark 1.2 | 90.7 |
| DeepSeek-V4-Flash-0731 | 90.2 |
| GLM-5.2 | 90.2 |
| Sonnet 4.6 | 90.0 |
| DeepSeek V4 Pro 0813 | 90.0 |
| Muse Spark | 90.0 |
| GPT-5.1 | 89.8 |
| GPT-5.4 | 89.8 |
| GPT-5.5 | 89.8 |
| GPT-5.6 Luna | 89.8 |
| Nemotron 3 Ultra 550B A55B (NVFP4) | 89.8 |
| Qwen3.6 Plus (2026-04-02) | 89.8 |
| Opus 4.1 | 89.5 |
| Sonnet 4.5 | 89.5 |
| GLM-5.1 | 89.5 |
| Sonnet 5 | 89.0 |
| DeepSeek-V4-Pro | 89.0 |
| Gemini 3.1 Flash-Lite Preview | 89.0 |
| GLM-5.3 | 89.0 |