MMLU Pro - Computer Science
General QA · 2024-06-03
The Computer Science split of MMLU Pro. This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 94.1 |
| Claude Opus 5 | 93.9 |
| Opus 4.7 | 92.7 |
| Opus 4.8 | 92.7 |
| Gemini 3.1 Pro Preview | 92.7 |
| Gemini 3.5 Flash | 91.7 |
| Gemini 3.6 Flash | 91.7 |
| Gemini 3 Pro Preview | 91.5 |
| Kimi K2.6 | 91.2 |
| Kimi K3 | 91.2 |
| Qwen3.7-Max | 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 |
| Opus 4.6 | 90.7 |
| GPT-5.6 Sol | 90.7 |
| Muse Spark 1.1 | 90.7 |
| GLM-5.2 | 90.2 |
| Sonnet 4.6 | 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 | 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 |
| Grok 4.3 | 89.0 |
| Kimi K2.5 | 89.0 |
| Inkling | 88.5 |
| Qwen3 Max Thinking (2026-01-23) | 88.5 |
| Opus 4 | 88.3 |
| GPT-5.2 | 88.3 |
| MiniMax M3 | 88.3 |