MAXIFE

MAXIFE - multilingual instruction following benchmark. Reports accuracy on English + multilingual original prompts (23 settings total).

Category

Multilingual

Max Score

—

Score Type

percent

Active

Yes

Model Scores

Scores for MAXIFE

Model Score Date Verified
Qwen3.5-4B
78.00
01.02.2026 Verified
Qwen3.5-122B-A10B
99.00%
01.02.2026 Verified
Qwen3.5-27B
100.00%
01.02.2026 Unverified
Qwen3.5-35B-A3B
86.00%
01.02.2026 Unverified
Qwen3-235B-A22B
52.00%
01.02.2026 Unverified
GPT-5-mini 2025-08-07
73.00%
01.02.2026 Unverified