live
weekly refresh
basedagi.org
benchmark evidence

Global-MMLU-Lite Average

Artificial Analysis multilingual knowledge benchmark averaged across 16 languages.

winner on Global-MMLU-Lite Average
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9646d)
latest mapped results | top 20
#ModelScoreEvidenceTested
1Anthropic: Claude Opus 4.6
Anthropic
92.2
model-only
independent_benchmark
2000-01-01
2Anthropic: Claude Opus 4.5
Anthropic
91.3
model-only
independent_benchmark
2000-01-01
3Anthropic: Claude Sonnet 4.6
Anthropic
90.5
model-only
independent_benchmark
2000-01-01
4Google: Gemini 2.5 Pro
Google
90.3
model-only
independent_benchmark
2000-01-01
5Anthropic: Claude Sonnet 4.5
Anthropic
89.3
model-only
independent_benchmark
2000-01-01
6Google: Gemini 2.5 Flash
Google
88.8
model-only
independent_benchmark
2000-01-01
7OpenAI: GPT-5.2
Openai
86.8
model-only
independent_benchmark
2000-01-01
8Anthropic: Claude Haiku 4.5
Anthropic
83.4
model-only
independent_benchmark
2000-01-01
9DeepSeek: DeepSeek V3.2
Deepseek
82.7
model-only
independent_benchmark
2000-01-01
10Meta: Llama 4 Maverick
Meta Llama
82.5
model-only
independent_benchmark
2000-01-01
11Z.ai: GLM 5
Z Ai
81.9
model-only
independent_benchmark
2000-01-01
12Meta: Llama 4 Scout
Meta Llama
74.1
model-only
independent_benchmark
2000-01-01
13MoonshotAI: Kimi K2 Thinking
Moonshotai
73.5
model-only
independent_benchmark
2000-01-01
what this result means

Artificial Analysis multilingual knowledge benchmark averaged across 16 languages.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on Global-MMLU-Lite Average. Broad task pages require independent corroboration before naming a general winner.

source record
category: multilingual
metric: accuracy
matched models: 13
latest source date: 2000-01-01
direction: higher is better
inspect upstream source ->