The AI tools index that doesn't waste your time.不浪费你时间的 AI 工具索引。
Knowledge · weight 15%知识 · 权重 15%

MMLU-Pro

saturation watchlist饱和观察名单 official site官网

What it tests: A harder re-build of the classic MMLU: 12K questions, 10 answer choices instead of 4, more reasoning-heavy, 14 domains. The original MMLU is saturated (>93%) and retired from our scoring.

考什么:经典 MMLU 的加难重制版:1.2 万题、10 个选项(原来 4 个)、更重推理、14 个学科。原版 MMLU 已饱和(>93%),我们不再计入评分。

Why it counts: Still the standard 'general knowledge' yardstick — but top models cluster within a few points, so we watch its saturation closely.

为什么算数:仍是'通用知识'的标准尺子,但头部模型分差已很小——我们已把它列入饱和观察名单,随时准备降权。

Maintainer维护方TIGER-AI-Lab
License许可Apache 2.0,需署名
Reference point (prior-gen SOTA)参考点(上一代 SOTA)85

Standings实时排名

30 models with sourced scores 个模型有溯源成绩
#Model模型Score成绩Index指数Dated日期Measured by测评方
1Grok 4.20xAI95100vendor-reported厂商自报source ↗
2Claude Opus 5Anthropic91.59962026-083rd-party第三方source ↗×3
3Claude Fable 5Anthropic91.5962026-08-193rd-party第三方source ↗×2
4Gemini 3.1 Pro PreviewGoogle89.8952026-08-143rd-party第三方source ↗×5
5Qwen3.7 MaxQwen89.6942026-083rd-party第三方source ↗×3
6Grok 4.5xAI89.2943rd-party第三方source ↗×2
7GPT-5.6 SolOpenAI89.1942026-083rd-party第三方source ↗×2⚠±6.1
8GLM 5.2Z.ai88.9942026-073rd-party第三方source ↗×2
9Qwen3.7 PlusQwen88.5932026-083rd-party第三方source ↗×3
10Kimi K2 ThinkingMoonshot AI87.572⚡high923rd-party第三方source ↗×2
11Claude Sonnet 5Anthropic87.55923rd-party第三方source ↗×3
12DeepSeek V4 Pro 0423DeepSeek87.5923rd-party第三方source ↗×5
13GLM 5.1Z.ai87923rd-party第三方source ↗×2⚠±5
14Nemotron 3 UltraNVIDIA86.8913rd-party第三方source ↗×2
15DeepSeek V4 Flash 0423DeepSeek86.2912026-083rd-party第三方source ↗×4
16GPT-5.5OpenAI86.1913rd-party第三方source ↗
17DeepSeek V3.2DeepSeek85893rd-party第三方source ↗×3
18MiniMax M2.7MiniMax82863rd-party第三方source ↗
19Mistral Medium 3.5Mistral AI81.3863rd-party第三方source ↗×2⚠±5.3
20Llama 4 MaverickMeta80.5853rd-party第三方source ↗×4
21gpt-oss-120bOpenAI79833rd-party第三方source ↗×3⚠±11
22MiniMax M3MiniMax78.1823rd-party第三方source ↗
23Gemini 3.1 Flash LiteGoogle78823rd-party第三方source ↗
24Command R+ (08-2024)Cohere75.7803rd-party第三方source ↗
25Sonar ProPerplexity75.5793rd-party第三方source ↗
26Mistral LargeMistral AI73.11773rd-party第三方source ↗
27Phi 4Microsoft71.4753rd-party第三方source ↗
28Command ACohere71.2753rd-party第三方source ↗
29Claude Haiku 4.5Anthropic65683rd-party第三方source ↗×2⚠±15
30Gemini 3.6 FlashGoogle55.35583rd-party第三方source ↗

How scores become the Intelligence Score →成绩如何合成智能评分 →