Emoji-Affect Decodability (Bangla): leaderboard

Metric: Macro-F1 (%; emoji-affect decodability: 5-fold cross-validated l2-regularised logistic regression on sublinear TF-IDF features of each model's emoji graphemes, predicting the source emotion label of the 4,206 single-label Bangla sentences over the five emotions shared by the three corpora; one generation per sentence at temperature 0.7; majority-class floor 8.7). Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.

Top models

#ModelScore
1Gemini 2.0 Flash65.7
2Grok 4 Fast65.5
3Gemma 3 27B (IT)65.3
4Mistral Large 363.9
5Qwen 3 VL 235B A22B59.7
6Claude 3 Haiku58.4
7GPT-4.1 Nano56.2
8DeepSeek V3.256

Interactive version: theaggregate.ai/benchmark?slug=emoji-affect-decodability-bangla · How It Works · Data refreshed daily, snapshot 2026-09-26.