List your company

Instruction Following on EQ-Bench Longform (ID prompts) (45 prompts)

1,911Elo ScoreGPT-5.4
755.561,055.531,355.51,655.47Jun 2, 2026

Evaluation results

MethodLinks
GPT-5.4Judge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,911
Claude Opus 4.6Judge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,774
GPT-5.4-miniJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,728
POLARIS–9BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,658
Gemini 3.1 ProJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,619
Gemini 3 FlashJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,612
GPT-5.4-nanoJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,563
Gemma 4 31BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,505
Qwen3.5-27BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,494
Gemma 4 26B-A4BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,451
Qwen3.5-9BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,343
Gemma 4 E4BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,301
Ministral-3-8BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,214
DeepSeek-R1-distill-Qwen-14BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,033
LongWriter-Zero-32BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.061,011
LongWriter-Llama3.1-8BJudge model=Gemini 3 Flash, Judge dimensions=11 dims + length, Comparison protocol=dual-position, Prompt count=452026.06800