Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following on EQ-Bench Longform (ID prompts) (45 prompts)
Loading...
1,911
Elo Score
GPT-5.4
755.56
1,055.53
1,355.5
1,655.47
Jun 2, 2026
Elo Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Elo Score
GPT-5.4
Judge model=Gemini 3 F...
2026.06
1,911
Claude Opus 4.6
Judge model=Gemini 3 F...
2026.06
1,774
GPT-5.4-mini
Judge model=Gemini 3 F...
2026.06
1,728
POLARIS–9B
Judge model=Gemini 3 F...
2026.06
1,658
Gemini 3.1 Pro
Judge model=Gemini 3 F...
2026.06
1,619
Gemini 3 Flash
Judge model=Gemini 3 F...
2026.06
1,612
GPT-5.4-nano
Judge model=Gemini 3 F...
2026.06
1,563
Gemma 4 31B
Judge model=Gemini 3 F...
2026.06
1,505
Qwen3.5-27B
Judge model=Gemini 3 F...
2026.06
1,494
Gemma 4 26B-A4B
Judge model=Gemini 3 F...
2026.06
1,451
Qwen3.5-9B
Judge model=Gemini 3 F...
2026.06
1,343
Gemma 4 E4B
Judge model=Gemini 3 F...
2026.06
1,301
Ministral-3-8B
Judge model=Gemini 3 F...
2026.06
1,214
DeepSeek-R1-distill-Qwen-14B
Judge model=Gemini 3 F...
2026.06
1,033
LongWriter-Zero-32B
Judge model=Gemini 3 F...
2026.06
1,011
LongWriter-Llama3.1-8B
Judge model=Gemini 3 F...
2026.06
800
Feedback
Search any
task
Search any
task