# GPT-4 Turbo vs GPT-5.6 Luna

As of Oct 15, 2026, GPT-4 Turbo leads GPT-5.6 Luna in 1 of 2 shared categories: General LLM.

GPT-4 Turbo: $15.000000000000002 per 1M blended tokens.

GPT-5.6 Luna: $0.44999999999999996 per 1M blended tokens.

GPT-4 Turbo: closed weights.

GPT-5.6 Luna: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, GPT-4 Turbo leads GPT-5.6 Luna in General LLM at #10 against #53.
- Which to pick, Science: As of Oct 15, 2026, GPT-5.6 Luna leads GPT-4 Turbo in Science at #25 against #139.

As of Oct 15, 2026, GPT-4 Turbo is ranked #10 in General LLM (since Oct 15, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).

As of Oct 15, 2026, GPT-5.6 Luna is ranked #16 in Coding (since Oct 15, 2026; sources Terminal-Bench 4.0; methodology v1.0).