MORPHOGEN - French Corpus Gender Accuracy: leaderboard

Gender-aware morphological generation in French on MORPHOGEN (2026): the model rewrites a first-person sentence for a speaker of the opposite grammatical gender while keeping its meaning, scored against human-corrected references. Corpus-level share of reference gendered terms generated correctly, in percent; higher is better.

Metric: Corpus-level gender accuracy (%): correctly generated gendered terms over all reference gendered terms of the test set, in the GENFORM task of MORPHOGEN: rewrite a first-person French sentence for a speaker of the opposite grammatical gender while keeping its meaning (both directions, human-corrected references), zero-shot with the model chat template, temperature 0.1; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4o Mini90.27#1680
2Phi-487.7#1951
3Llama 3.1 8B81.76#5193
4Gemma 3 27B79.63#1672
5Llama 3.3 70B76.08#1523
6Qwen 3 32B74.74#983
7Gemma 3 12B74.26#2091
8Qwen 3 14B73.91#1284
9Qwen 3 8B69.91#1890
10Gemma 2 9B55.56#3259
11Llama 3.2 3B53.48#7835
12Qwen 3 4B53.2#2379
13Gemma 3 4B51.6#5347
14Gemma 2 2B37.54#8407
15Qwen 2.5 0.5B4.16#9146

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=morphogen-french-corpus-gender-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-22.