Share your thoughts, 1 month free Claude Pro on usSee more

Coding on WildChat 5,000 conversations

0.26KL Divergence (Forward)

Gemini 3.1 Pro

Updated 22d ago

Evaluation Results

Method	Links
Gemini 3.1 Pro 2026.05		0.26	0.256	0.246
GPT-5.4 2026.05		0.261	0.265	0.248
humanlm-opinion 2026.05		0.268	0.257	0.247
gemma-4-31B-it 2026.05		0.311	0.296	0.297
UserLM-8b 2026.05		0.328	0.388	0.349
GPT-5.4 nano 2026.05		0.353	0.364	0.353
Gemini 3 Flash 2026.05		0.355	0.328	0.334
gpt-oss-120b 2026.05		0.358	0.353	0.343
GPT-5.4 mini 2026.05		0.363	0.388	0.364
Qwen3.5-122B-A10B 2026.05		0.394	0.378	0.387
gemma-4-26B-A4B-it 2026.05		0.397	0.373	0.379
gpt-oss-20b 2026.05		0.411	0.435	0.409
gemma-4-E4B-it 2026.05		0.422	0.383	0.402
Gemini 3.1 Flash-Lite 2026.05		0.432	0.406	0.421
Llama-3.1-8B-Instruct 2026.05		0.435	0.427	0.423
Qwen3.5-27B 2026.05		0.437	0.421	0.433
Claude Haiku 4.5 2026.05		0.438	0.43	0.427
gemma-4-E2B-it 2026.05		0.446	0.435	0.435
Qwen3.5-9B 2026.05		0.465	0.457	0.454
Llama-3.3-70B-Instruct 2026.05		0.471	0.456	0.469
Qwen3.5-35B-A3B 2026.05		0.48	0.467	0.478
Qwen3.5-4B 2026.05		0.482	0.471	0.472
Qwen3.5 .8B 2026.05		0.547	0.568	0.579
Qwen3.5-2B 2026.05		0.584	0.591	0.608