⌘K

Compare models

Pick up to three models.

Claude Fable 5 Claude Haiku 4.5 Claude Opus 4.8 Claude Sonnet 5 DeepSeek V3.2 DeepSeek V4 Pro Gemini 2.5 Flash Gemini 3 Pro GPT-5.1 GPT-5.6 Sol Grok 4.1 Grok 4.5 Kimi K2 Kimi K3 Llama 4 Maverick Meta Muse Spark 1.1 Mistral Large 3 Qwen3 235B Qwen3.8-Max

	Claude Haiku 4.5	DeepSeek V3.2
AA Intelligence Index	24	25
Context window	200K tokens	128K tokens
Input $/MTok	$1 / MTok	$0.28 / MTok
Output $/MTok	$5 / MTok	$0.42 / MTok
Modalities	text, image, code	text, code
API	Yes	Yes
Open source	No	Yes

Intelligence Index scores are sourced from Artificial Analysis, an independent evaluator — not Timace's own judgment.