RankingIA v0.6.1
EN

Apertus 8B Instruct

Swiss AI Initiative

39.2#265 of 427 overall
Input / output
US$ 0,10 / US$ 0,20
US$ per 1M tokens
Context
—
tokens
Release
09/02/2025
release date
Weights
—
 
Speed
152 tok/s
first token in 2.46 s

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
Humanity's Last Exam weight 1 5.0 28% Artificial Analysis
GPQA Diamond 25.6 4% Artificial Analysis
Long-context reasoning 0.0 6% Artificial Analysis

By category

CategoryScoreRankMetrics
Reasoning27.3#381Humanity's Last Exam, GPQA Diamond
Research28.2#338Long-context reasoning

History

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.

Compare with other models

At the sources