Humanity's Last PRD: the AI benchmark for product managers

GPT-6 Astra leads by 2 points.

Combined score by model and task type. Choose a column heading to sort by that task.
Model		Product Craft						Growth				Metrics & Experimentation				Strategy						Leadership
Model
GPT-6 AstraOpenAI	90#1	96Best	81	84Best	97	70	89	91Best	84	100Best	98Best	79	98Best	91	99Best	87Best	88	92	93	96Best	86	94Best	86	91Best
GPT-6.1 SolOpenAI	88#2	95	85	71	98Best	89	91	89	87	84	97	75	83	96	99	77	91	89	93	80	81	88	96Best	89
Sonnet 5.5Anthropic	87#3	80	86Best	77	94	93Best	94Best	90	90Best	84	88	95Best	92	96Best	92	78	78	81	83	85	84	90	92	81
Haiku 5.5Anthropic	84#4	77	77	67	86	92	92	82	70	82	96	89	78	86	96	80	92	93Best	80	81	76	89	79	91
Opus 5.5Anthropic	82#5	72	82	65	94	77	91	82	72	91	92	81	84	86	82	71	62	84	94Best	82	89Best	81	83	87
GPT-6 LunaOpenAI	81#6	87	77	65	87	85	77	86	66	90	98	76	75	92	82	74	93Best	84	86	79	68	71	82	82
Gemini 3.8 FlashGoogle	61#7	66	58	39	68	76	55	56	61	77	71	60	55	71	61	61	50	43	60	63	51	58	69	82
Gemini 3.5 Flash-LiteGoogle	49#8	56	41	39	44	49	52	44	35	68	74	29	53	44	51	49	50	40	41	56	42	60	60	61

Combined scoreEach cell is the model’s best setup on that task type.

Tested with criteria sourced from the very best.

We carefully research and design the rubric for each task around the advice of guests on Lenny’s Podcast.

30 product leaders behind the checks

We credit their ideas. None of them has reviewed or endorsed the benchmark.

Show

GPT-6.1 Sol · API scores within 2 points of GPT-6 Astra · ChatGPT at a fifth of the cost.

Best valueNobody beats these on both score and costCost partly estimated (app runs with no usage meter)At least one critical failure