live
weekly refresh
basedagi.org
benchmark evidence

AI Language Proficiency Monitor Spanish

Mean ARC, MGSM, and MMLU accuracy for Spanish, from the AI Language Proficiency Monitor.

winner on AI Language Proficiency Monitor Spanish
direct benchmark result, not a broad vertical composite | source row dated 2026-05-19
scored on 2026-05-19
latest mapped results | top 20
#ModelScoreEvidenceTested
1OpenAI: GPT-5.2
Openai
100.0
model-only
independent_benchmark
2026-05-19
2OpenAI: GPT-5.4
Openai
100.0
model-only
independent_benchmark
2026-05-19
3Anthropic: Claude Opus 4.5
Anthropic
100.0
model-only
independent_benchmark
2026-05-19
4Anthropic: Claude Sonnet 4
Anthropic
100.0
model-only
independent_benchmark
2026-05-19
5Qwen: Qwen3 30B A3B
Qwen
100.0
model-only
independent_benchmark
2026-05-19
6OpenAI: GPT-5.1
Openai
100.0
model-only
independent_benchmark
2026-05-19
7Anthropic: Claude Sonnet 4.6
Anthropic
100.0
model-only
independent_benchmark
2026-05-19
8Anthropic: Claude Opus 4.6
Anthropic
100.0
model-only
independent_benchmark
2026-05-19
9Amazon: Nova Pro 1.0
Amazon
96.7
model-only
independent_benchmark
2026-05-19
10Anthropic: Claude Haiku 4.5
Anthropic
96.7
model-only
independent_benchmark
2026-05-19
11Anthropic: Claude Sonnet 4.5
Anthropic
96.7
model-only
independent_benchmark
2026-05-19
12OpenAI: GPT-5
Openai
96.7
model-only
independent_benchmark
2026-05-19
13Google: Gemini 2.5 Pro
Google
96.7
model-only
independent_benchmark
2026-05-19
14OpenAI: GPT-4.1
Openai
96.7
model-only
independent_benchmark
2026-05-19
15Meta: Llama 4 Maverick
Meta Llama
90.0
model-only
independent_benchmark
2026-05-19
16Meta: Llama 3.3 70B Instruct
Meta Llama
80.0
model-only
independent_benchmark
2026-05-19
17Mistral: Mistral Nemo
Mistralai
70.0
model-only
independent_benchmark
2026-05-19
18Google: Gemini 2.5 Flash
Google
40.0
model-only
independent_benchmark
2026-05-19
what this result means

Mean ARC, MGSM, and MMLU accuracy for Spanish, from the AI Language Proficiency Monitor.

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

A win here is a win on AI Language Proficiency Monitor Spanish. Broad task pages require independent corroboration before naming a general winner.

source record
category: multilingual
metric: accuracy
matched models: 18
latest source date: 2026-05-19
direction: higher is better
inspect upstream source ->