ModelVerdict

Tested models

Every model we measure on business documents. Click a model to see its results, errors, and cost.

ModelVendorReads imagesOpen weightsList price per 1M tokens (input / output)
Claude Haiku 5.5Anthropicyesno$0.10 / $0.50
Claude Sonnet 5Anthropicyesno$2.00 / $10.00
Claude Sonnet 5.5Anthropicyesno$2.00 / $10.00
DeepSeek V4.1 FlashDeepSeekyesyes$0.30 / $1.20
Gemini 3.5 Flash LiteGoogleyesno$0.30 / $2.50
Gemini 3.8 FlashGoogleyesno$0.75 / $3.75
Gemma 4 31BGoogleyesyes$0.09 / $0.34
Mistral Large 4Mistralyesno$0.68 / $2.09
Mistral Medium 3.5Mistralyesno$1.50 / $7.50
Mistral Small 4Mistralyesyes$0.15 / $0.60
GPT-6 LunaOpenAIyesno$0.10 / $0.50
GPT-6 SolOpenAIyesno$2.00 / $10.00
Qwen3.8 FlashQwenyesno$0.15 / $0.47
GLM-5.3 FlashZ.aiyesyes$0.15 / $0.50

Log in with email

We use your email only to log you in (and for the digest if you tick it). No spam.