Home / Benchmarks / MMLU-Pro
Benchmark leaderboard
MMLU-Pro
A harder, 10-option successor to MMLU across 14 subjects, ~12,000 questions.
| # | Model | Maker | Score | Measured | Link |
|---|---|---|---|---|---|
| 1 | Qwen3.8-Max | Alibaba Qwen | 88.6 / 100 | Oct 14, 2026 | Source |
| 2 | GPT-5 | OpenAI | 86.5 / 100 | Oct 14, 2026 | Source |
| 3 | GPT-5.6 Luna | OpenAI | 86.0 / 100 | Oct 14, 2026 | Source |
| 4 | Gemini 3.5 Flash-Lite | Google DeepMind | 85.8 / 100 | Oct 14, 2026 | Source |
| 5 | Grok 4.3 | xAI (SpaceXAI) | 85.8 / 100 | Oct 14, 2026 | Source |
| 6 | Nemotron 3 Ultra 550B-A55B | NVIDIA | 85.8 / 100 | Oct 14, 2026 | Source |
| 7 | DeepSeek V4 Pro (0813) | DeepSeek | 82.9 / 100 | Oct 14, 2026 | Source |
| 8 | Nemotron 3 Nano 30B-A3B | NVIDIA | 78.3 / 100 | Oct 14, 2026 | Source |
Scores are the benchmark owners’ published results, recorded with the date we verified them. This benchmark feeds the League Score — see methodology.