Skip to content

Benchmark

Baromètre IA French Writing (AI judges)

People compare model answers and choose which they prefer. Scores are index points out of 100. Higher is better.

Models measured
76
Scores recorded
111
Sources
1
IQ weight
1.51

Score distribution

52.2
Mean
54.9
Median
29.6
Std dev
7.8
10th percentile
92.6
90th percentile
1.2
Min
1.299
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.51 for chat models, measured over 76 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Gemma 4 E2B ITgemma-4-e2b-it-q8_0::disabled· Baromètre de l’écriture IA data docs7.8
102Gemma 4 E2B ITgemma-4-e2b-it-q8_0::enabled· Baromètre de l’écriture IA data docs7.7
103Qwen3.6 35B A3Bqwen3.6-35b-a3b-it-q4_k_m::disabled· Baromètre de l’écriture IA data docs7.4
104Granite 4.2 30Bgranite-4.2-30b-q8_0::enabled· Baromètre de l’écriture IA data docs7
105Gemma 4 E2B ITgemma-4-e2b-it-q4_k_m::enabled· Baromètre de l’écriture IA data docs6.4
106MiniMax M3.1 Flashminimax-m3.1-flash-high::enabled· Baromètre de l’écriture IA data docs5.5
107gemma 4 E4Bgemma-4-e4b-it-q4_k_m::enabled· Baromètre de l’écriture IA data docs5.3
108Gemma 4 E2B ITgemma-4-e2b-it-q4_k_m::disabled· Baromètre de l’écriture IA data docs5
109Granite 4.2 30Bgranite-4.2-30b-q4_k_m::enabled· Baromètre de l’écriture IA data docs3.5
110Granite 4.2 8Bgranite-4.2-8b-q8_0::enabled· Baromètre de l’écriture IA data docs1.4
111Granite 4.2 8Bgranite-4.2-8b-q4_k_m::enabled· Baromètre de l’écriture IA data docs1.2

Showing 101–111 of 111 results.

Data credits: Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated