Claude Haiku 4.5 vs GPT-5.1-Codex-Mini

Compare Claude Haiku 4.5 by Anthropic against GPT-5.1-Codex-Mini by OpenAI, in 184 community votes, claude haiku 4.5 wins 60% of head-to-head duels, context windows of 200K vs 400K, tested across 52 shared challenges. Updated February 2026.

In 184 community votes, Claude Haiku 4.5 wins 60% of head-to-head duels. Claude Haiku 4.5 leads in Image Generation, Analysis, while GPT-5.1-Codex-Mini leads in Reasoning. Based on blind community voting from the RIVAL open dataset of 184+ human preference judgments for this pair.