List your company

Creative Writing on EQ-Bench Longform (32 prompts)

1,578Elo RatingGPT-5.4
768.88978.941,1891,399.06Jun 2, 2026

Evaluation results

MethodLinks
GPT-5.4Judge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,578
Claude Opus 4.6Judge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,464
GPT-5.4-miniJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,463
HumanJudge model=Gemini 3 Flash, Comparison protocol=dual-position, Prompt count=322026.061,460
POLARIS–9BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,416
Gemini 3.1 ProJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,380
Gemini 3 FlashJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,326
Gemma 4 31BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,275
GPT-5.4-nanoJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,275
Qwen3.5-27BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,275
Gemma 4 26B-A4BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,228
Gemma 4 E4BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,100
Qwen3.5-9BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,078
Ministral-3-8BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.061,049
DeepSeek-R1-distill-Qwen-14BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.06894
LongWriter-Llama3.1-8BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.06871
LongWriter-Zero-32BJudge model=Gemini 3 Flash, Judge dimensions=9 dims, Comparison protocol=dual-position, Prompt count=322026.06800