Tasks / Leadership

Write a performance review

Can the model write a review that is clear, fair and specific enough to change what the person does next?

Task type v1.1 · 2 tasksLast changed 6 Oct 2026 · ChangelogDifficulty

What AI gets right here, and what you’ll still have to catch

From 16 graded outputs by 8 models. 50% were usable with at most a quick edit.

Reliably right

Judges outcomes, not activity100% pass
Every rating change and keep is justified by outcomes against goals, with shipping and activity treated as context, not the result.
GPT-6 Astra · ChatGPT · Fourteen ratings, three managers
Owns the manager's part100% pass
Ana plainly acknowledges her Q3 mistake and commits to reviewing goal metrics first in every monthly 1:1.
Opus 5.5 · Claude · Shipped a lot, moved nothing
Clear and direct, with care97% pass
The note to Ravi is direct, specific about what needs to change, and framed to help him succeed; the whole pre-read is clear and actionable.
GPT-6 Astra · ChatGPT · Fourteen ratings, three managers

Where it slips

Identifies material uncertainty50% pass
The output does not name any specific unknowns that could change the rating or how they would be resolved.
Opus 5.5 · Claude · Shipped a lot, moved nothing
Notices who's underrated69% pass
It does not propose Exceeds or ask Sara to justify Meets despite Nora beating both goals; it merely keeps Meets, missing the underrating.
GPT-6 Luna · API · Fourteen ratings, three managers
Catches the inflated team78% pass
The output proposes lowering Ben from Exceeds to Meets, failing to keep Ben at Exceeds as required; Ben beat both outcome goals and should remain Exceeds.
Opus 5.5 · Claude · Fourteen ratings, three managers

How it’s graded

Each check is built on how world-class product and growth leaders do this work, as they’ve described it on Lenny’s Podcast, and names the leader it comes from.

Clear and direct, with care
Does the review say plainly what needs to change, in words the person couldn't misread, while showing it is written to help them succeed?
Passes when Every main point is stated directly, with the specific change expected and the support on offer.
Kim ScottLenny’s Podcast
Judges outcomes, not activity
Does the review judge the person on the outcomes they achieved against their goals, rather than on how much they shipped or how busy they were?
Passes when Rates against the goals' outcomes, with the evidence, and treats output as context, not the result.
Product and growth leadersOn Lenny’s Podcast
Names gaps you could see
Is each area to improve described as specific, observable behaviour with what good would look like, rather than labels like 'be more strategic'?
Passes when Every gap names what the person did or didn't do, in a specific situation, and what doing it well would look like.
Product and growth leadersOn Lenny’s Podcast
Weighs the whole period
Does the review weigh the whole review period, rather than letting one recent event or one strong impression decide the verdict?
Passes when Covers the whole period in proportion, and explicitly guards against a recent event or one impression dominating.
Product and growth leadersOn Lenny’s Podcast

Plus our standard checks

Uses the supplied evidence correctly · Addresses the actual decision · Respects explicit constraints · Identifies material uncertainty · Avoids unsupported claims · Produces the required deliverable · and 3 written for each task, which you’ll see in the tasks below.

The tasks

Read the brief, then compare up to three outputs, each with the LLM judge’s verdict on every check. Highlights mark what a PM had to fix.

The brief

You're the Director of Product at Northgate, and you're facilitating Thursday's calibration for 14 PMs across three managers (Ravi, Sara and Tom). Write the pre-read, in no more than 1,100 words: the ratings you'd change and why, each with the evidence, the ones you'd keep, and a short note to Ravi about his ratings. Use the guidance below.\n\nThe proposed ratings and evidence are attached.

What the model was given2 items: calibration_guidance.md, proposed_ratings.csv (one row per PM, as each manager submitted it)

calibration_guidance.md7 lines · Download

# Calibration guidance

- Ratings judge outcomes against goals first, then how the work was done. Shipping is not an outcome.
- Any rating other than Meets needs written evidence of outcomes.
- A Below rating needs documented earlier feedback on the gap.
- Expected spread across the org: most PMs Meets; Exceeds for clear outperformance on outcomes.
- The calibration facilitator proposes changes; managers can respond before ratings are final.

proposed_ratings.csv (one row per PM, as each manager submitted it)pm,manager,proposed_rating,goal_1,goal_1_result,goal_2,goal_2_result,evidence_cited_by_manager Aisha,Ravi,Greatly exceeds,Raise trial conversion 8% to 11%,8.4%,Ship self-serve billing,Shipped,Shipped 9 features; great energy; leadership loves her Ben,Ravi,Exceeds,Cut onboarding time 10 to 5 days,4.5 days,Raise activation 30% to 38%,39%,Hit both goals Chloe,Ravi,Exceeds,Grow API usage 20%,+4%,Launch partner portal,Shipped,Partner portal launched on time; strong specs Dev,Ravi,Exceeds,Reduce support tickets per account 25%,-27%,NPS from 31 to 40,41,Hit both goals; mentored two APMs Emma,Ravi,Exceeds,Expansion revenue +15%,+6%,Ship usage dashboard,Shipped,Very responsive to Sales; shipped 6 Sales requests Femi,Sara,Meets,Raise weekly retention 41% to 46%,46%,Cut churn of new accounts 20%,-22%,"Hit both goals, steady" Gita,Sara,Below,Raise invoices paid online 35% to 45%,47%,Launch reminders v2 by September,"Launched, rolled back after 4 days (support not briefed)",Reminders launch in September was a mess Hugo,Sara,Meets,Ship mobile app v2,Shipped late,Mobile weekly actives +20%,+3%,Delivered a hard project Ines,Tom,Exceeds,Cut checkout drop-off 30% to 22%,21%,Launch two payment methods,Shipped,"Hit both, specific evidence" Jon,Tom,Meets,Search success 60% to 70%,66%,Ship filters,Shipped,"Good progress, more to do" Kai,Tom,Meets,Reduce refund rate 4% to 3%,3.1%,Fraud losses -20%,-24%,Solid year Lena,Tom,Below,Grow marketplace listings 25%,+9%,Launch seller analytics,Not launched,"Missed both goals; feedback given in Q2 and Q3 1:1s, documented" Mo,Tom,Meets,Cut time to first sale for new sellers 21 to 14 days,15 days,Seller NPS +5,+6,"Nearly hit, good stakeholder work" Nora,Sara,Meets,Raise payment success 92% to 95%,95.4%,Cut payment support tickets 30%,-35%,"Quiet, delivered"

What a strong answer doesThe answer key the graders mark against

Judges each PM on outcomes against their goals, as the guidance says. Ravi rated all five of his PMs Exceeds or above, but only Ben and Dev hit both goals; Aisha (Greatly exceeds) missed her conversion goal (8.4% against 11%), Chloe missed API usage (+4% against +20%) and Emma missed expansion (+6% against +15%), and his evidence is output ('shipped 9 features', 'responsive to Sales'). Proposes Aisha, Chloe and Emma at Meets (or lower for Chloe, whose outcome goal was far off), keeps Ben and Dev at Exceeds. Gita (Sara, Below) beat her main goal (47% against 45%) and the Below rests on one September launch, with no documented feedback, which the guidance requires: Meets, with the launch-readiness gap documented now. Nora (Sara, Meets) beat both goals: a candidate for Exceeds. Lena (Tom, Below) has documented feedback and missed both goals: Below stands. Hugo shipped late and missed his outcome: Meets is generous but defensible, or Below needs documentation first. The note to Ravi is direct and respectful: rate on outcomes, not activity, with what evidence he'd need.

Critical failures (cap the score at 40)

Keeps Aisha at Greatly exceeds

Task

Staff-level · v1.0

The outputs

8 setups answered this brief.

GPT-6 AstraChatGPT100Usable with a quick edit GPT-6.1 SolAPI100Usable with a quick edit Haiku 5.5API100Usable with a quick edit Gemini 3.8 FlashAPI98Usable with a quick edit Opus 5.5Claude88Needs more work GPT-6 LunaAPI82Needs more work Sonnet 5.5API77Needs more work Gemini 3.5 Flash-LiteGemini38Needs more work

Haiku 5.5API

Usable with a quick edit13 of 13 checks passed

The pre-read gives specific changes, evidence, and a clear note to Ravi; it can be used with light edits and does not require re-checking facts.

Output

Calibration pre-read: 14 PMs, Ravi / Sara / Tom

Purpose: Thursday's calibration. Managers can respond to these proposals before ratings are final.

Rules I applied (from calibration guidance): - Ratings start from outcomes against goals. Shipping is an output, and it doesn't count as an outcome. - Any rating other than Meets needs written outcome evidence. - Below needs documented earlier feedback on the gap. Where that's missing, I've capped the rating at Meets. - Working definition for Exceeds (for discussion): both outcome goals beaten. One beat and one hit is Meets.

Summary: 6 changes, 1 hold, 7 keeps. Proposed spread after changes: 3 Exceeds, 10 Meets, 1 Below.

---

Ratings I'd change

Aisha (Ravi): Greatly exceeds → Meets - Trial conversion reached 8.4% against an 11% target. That's about 13% of the intended 3-point lift. - "Shipped self-serve billing" is an output. Nine features shipped is also an output. - "Great energy" and "leadership loves her" are not outcome evidence. - Greatly exceeds is not supported. Below would need documented feedback on the conversion gap, which the submission doesn't cite.

Chloe (Ravi): Exceeds → Meets - API usage grew 4% against a 20% target, which is one-fifth of the goal. - The partner portal shipped on time. That's an output, and it doesn't offset the miss. - "Strong specs" describes how the work was done, not what it achieved. - Ravi should show what the portal changed in usage, if anything. If the outcome is attributable and I've missed it, I'll revisit.

Emma (Ravi): Exceeds → Meets - Expansion revenue grew 6% against a 15% target, which is 40% of the goal. - The usage dashboard shipped, and six Sales requests were delivered. Both are outputs. Responsiveness to Sales is a good working habit, but it isn't an outcome.

Ines (Tom): Exceeds → Meets (open to revisiting) - Checkout drop-off reached 21% against a 22% target. That's a clean beat, but only by one point. - Two payment methods shipped. The record has no adoption or conversion metric for them, so that goal is an output. - Under the working definition, one beat plus one output is Meets. If Tom has adoption data for the new payment methods, I'll revisit Exceeds on Thursday.

Nora (Sara): Meets → Exceeds - Payment success reached 95.4% against a 95% target. - Payment-related support tickets fell 35% against a 30% target. - Both outcome goals were beaten, the same pattern as Ben. "Quiet" isn't a criterion, and the outcomes support a higher rating than proposed.

---

Ratings on hold (need documentation before Thursday)

Gita (Sara): Below → Meets (Below only if documentation exists) - Invoices paid online reached 47% against a 45% target. That's an outcome hit. - Reminders v2 launched, was rolled back after four days, and support wasn't briefed. That's a real failure in how the work was done, and it needs a written account and a postmortem. - Below requires documented earlier feedback on the gap. None is cited, and one of two outcome goals was hit. - Sara: if you have documented feedback on the launch-readiness issue, I'll reconsider Below.

Hugo (Sara): Meets (hold) - Mobile weekly actives grew 3% against a 20% target, which is 15% of the goal. The app shipped late. - "Delivered a hard project" is an output description, and the outcome miss is large. - Meets is the ceiling the current record supports. If the mobile gap was raised in 1:1s before Q3, Below is defensible. Sara, please confirm before Thursday.

---

Ratings I'd keep

PM	Rating	Why
Ben (Ravi)	Exceeds	Both beaten: onboarding 4.5 days vs 5; activation 39% vs 38%. Cite the numbers, not "hit both goals."
Dev (Ravi)	Exceeds	Both beaten: support tickets per account −27% vs −25%; NPS 41 vs 40. Mentoring two APMs is a useful addition.
Femi (Sara)	Meets	Retention exactly at target (46%); churn beat (−22% vs −20%). One beat, one hit.
Jon (Tom)	Meets	Search success 66% vs 70%, about 60% of the gain. Filters shipped. Partial progress is Meets.
Kai (Tom)	Meets	Refund rate 3.1% vs 3.0%, a narrow miss. Fraud losses −24% vs −20%, a beat.
Lena (Tom)	Below	Both goals missed (listings +9% vs +25%; seller analytics not launched). Feedback documented in Q2 and Q3 1:1s. Tom, please attach those notes to the file.
Mo (Tom)	Meets	Time to first sale 15 days vs 14 target, about 86% of the gain. Seller NPS +6 vs +5.

---

Note to Ravi

Ravi, five of your five ratings are above Meets, and three of them (Aisha, Chloe, Emma) rest on shipping, responsiveness and reputation. The outcome numbers in the same rows don't support those ratings: 8.4% vs 11%, +4% vs +20%, and +6% vs +15%.

Ben and Dev are your strongest calls because their evidence is outcomes, and that's the standard we should use for all five.

I'm not suggesting Aisha, Chloe or Emma had weak years. Nine features and an on-time portal are real work. But ratings have to be tied to the goals we set.

Before Thursday, could you: 1. For Aisha, Chloe and Emma, write the outcome analysis for each goal. Include what was tried, what moved, and what you think caused the gap. 2. Tell us whether any feedback on those gaps was documented earlier in the year. If it was, Below becomes available. 3. Respond to the proposed changes, so we can settle them on Thursday.

Happy to walk through this 1:1 before the session.

---

Expected spread after changes

Greatly exceeds: 0
Exceeds: 3 (Ben, Dev, Nora)
Meets: 10
Below: 1 (Lena), with Gita and Hugo pending documentation

This is within the guidance: most PMs at Meets, Exceeds reserved for clear outperformance on outcomes.

Grades and run details

Decision model 100 · LLM judge 100

Decision model checks

passUses the supplied evidence correctly70%
passAddresses the actual decision86%
passRespects explicit constraints33%
passIdentifies material uncertainty98%
passAvoids unsupported claims67%
passProduces the required deliverable85%
passCatches the inflated team100%
passRescues Gita from one bad launch100%
passNotices who's underrated100%
passClear and direct, with care100%
passJudges outcomes, not activity100%
passNames gaps you could see79%
passWeighs the whole period79%

Run

Run: #1
API response time: 47 s
Submitted: 8 Oct 2026

Gemini 3.5 Flash-LiteGemini

Needs more than a quick edit2 of 13 checks passed

The output is incomplete, missing the keep list and Ravi note, and cannot be used without redoing the reasoning and filling major gaps.

Output

To: Ravi, Sara, Tom From: Director of Product Subject: Pre-Read: Thursday PM Calibration (Northgate)

Team,

Ahead of our calibration session this Thursday, I have reviewed the proposed ratings, outcomes, and evidence for all 14 PMs across our org.

Per our calibration guidance, we evaluate PMs first on outcomes against goals, not on activity. Shipping features, being responsive to sales, or having great energy are inputs, not results. Furthermore, any rating other than "Meets" requires rigorous, quantifiable evidence of goal achievement, and "Below" ratings require documented prior feedback.

Below is my proposed adjustment of ratings, the rationale and evidence for changes, and the list of ratings we are keeping as submitted.

---

Part 1: Proposed Rating Changes & Rationale

#### 1. Aisha (Manager: Ravi) * Proposed by Manager: Greatly Exceeds * My Proposed Rating: Below * Evidence & Rationale: * Goal 1: Raise trial conversion from 8% to 11% $\rightarrow$ Result: 8.4% (Missed by a wide margin). * Goal 2: Ship self-serve billing $\rightarrow$ Result: Shipped (Violation of guidance: "Shipping is not an outcome"). * Rationale: Aisha missed her primary core metric goal entirely (gaining only 0.4% against a 3% target) and fell back on "shipping" and "great energy" for her second goal. Per our framework, failing the core quantitative goal while relying on output means this is a Below performance. Ravi, we will need to document the performance gap and prior feedback for Aisha in this cycle.

#### 2. Chloe (Manager: Ravi) * Proposed by Manager: Exceeds * My Proposed Rating: Meets * Evidence & Rationale: * Goal 1: Grow API usage 20% $\rightarrow$ Result: +4% (Severe miss). * Goal 2: Launch partner portal $\rightarrow$ Result: Shipped on time

Grades and run details

Decision model 65 · LLM judge 14

Decision model checks

passUses the supplied evidence correctly70%
passAddresses the actual decision28%
partialRespects explicit constraints20%
failIdentifies material uncertainty88%
passAvoids unsupported claims33%
partialProduces the required deliverable75%
partialCatches the inflated team95%
failRescues Gita from one bad launch83%
failNotices who's underrated95%
passClear and direct, with care55%
passJudges outcomes, not activity98%
passNames gaps you could see69%
passWeighs the whole period21%

Run

Run: #1
Time to output: 3 s
Submitted: 5 Oct 2026

GPT-6 AstraChatGPT

Usable with a quick edit13 of 13 checks passed

The pre-read is evidence-based, complete, and directly actionable; a PM could use it with minor wording tweaks without rechecking facts or redoing reasoning.

Output

Thursday calibration pre-read

From: Director of Product, Northgate Scope: 14 PMs across Ravi, Sara and Tom

These are my proposed changes, not final decisions. Please respond before Thursday with missing outcome evidence, relevant goal context, or documented earlier feedback that could change the assessment.

Standard I’m applying

We rate outcomes against goals first, then how the work was done. Shipping, responsiveness, visibility and strong execution matter, but do not substitute for impact.

For Exceeds, I’m looking for clear outperformance—not simply delivery or attainment. On this evidence, exceeding both measurable outcome goals supports Exceeds; meeting one and modestly beating another generally supports Meets. A modest beat on one outcome plus a shipped deliverable is not enough by itself.

A Below requires both evidence of underperformance and documented earlier feedback. Where that feedback is absent from the packet, I am not proposing Below. That does not mean the missed goals are acceptable or should go unaddressed.

Ratings I propose changing

PM	Proposed change	Evidence and rationale
Aisha — Ravi	Greatly exceeds → Meets	Trial conversion rose from 8% to 8.4%, against 11%. Self-serve billing shipped, but no resulting customer or business impact is supplied. Nine features, energy and leadership enthusiasm do not establish exceptional outcomes. The conversion miss is substantial; however, the packet contains no documented earlier feedback supporting Below.
Chloe — Ravi	Exceeds → Meets	API usage grew 4%, against 20%. The partner portal launched on time, and strong specifications support execution quality, not outcome outperformance. There is no written evidence supporting Exceeds or documented earlier feedback supporting Below.
Emma — Ravi	Exceeds → Meets	Expansion revenue grew 6%, against 15%. Shipping the dashboard and six Sales requests, plus responsiveness to Sales, do not offset the revenue shortfall without evidence of impact. No documented earlier feedback is supplied to support Below.
Gita — Sara	Below → Meets	Online invoice payment reached 47%, above the 45% target from a 35% baseline. Reminders v2 was rolled back after four days because Support was not briefed—a meaningful execution failure. We should account for that failure, but not let it erase the payment outcome. The packet also lacks the documented earlier feedback required for Below. Please bring any evidence of rollback impact and prior feedback.
Ines — Tom	Exceeds → Meets	Checkout drop-off fell from 30% to 21%, against 22%: a strong result, modestly above target. Two payment methods shipped, but shipment is not a second outcome. On the supplied evidence, this is solid attainment rather than clear overall outperformance. Incremental adoption, conversion or revenue evidence could change the assessment.
Nora — Sara	Meets → Exceeds	Payment success reached 95.4%, against 95% from 92%; payment-support tickets fell 35%, against 30%. She exceeded both measurable outcome goals. That warrants the same recognition as comparable performance elsewhere. “Quiet” is not a reason to discount demonstrated impact.

Ratings I propose keeping

PM	Rating	Evidence and rationale
Ben — Ravi	Exceeds	Onboarding fell from 10 to 4.5 days, beating 5 days; activation reached 39%, beating 38% from 30%. Both outcome goals were exceeded.
Dev — Ravi	Exceeds	Support tickets per account fell 27%, against 25%; NPS rose from 31 to 41, against 40. Both outcome goals were exceeded. Mentoring two APMs reinforces the assessment of how he worked; it is not the basis for the rating.
Femi — Sara	Meets	Weekly retention reached 46%, exactly on target from 41%; new-account churn fell 22%, against 20%. Strong delivery against goals, with a modest beat on one—not enough evidence of clear overall outperformance.
Hugo — Sara	Meets, pending feedback review	Mobile weekly actives grew 3%, against 20%, and app v2 shipped late. “A hard project” does not establish successful outcomes. This is a material performance concern, but the packet lacks documented earlier feedback needed for Below.
Jon — Tom	Meets	Search success improved from 60% to 66%, short of 70%. Filters shipped, but no incremental impact is given. There is neither evidence for Exceeds nor documented earlier feedback supporting Below. The remaining outcome gap needs explicit follow-up.
Kai — Tom	Meets	Refund rate reached 3.1%, narrowly missing 3% from 4%; fraud losses fell 24%, beating 20%. Mixed attainment supports Meets.
Lena — Tom	Below	Listings grew 9%, against 25%, and seller analytics did not launch. The packet documents feedback in Q2 and Q3 1:1s. Both the performance evidence and earlier-feedback requirement are present.
Mo — Tom	Meets	Time to first sale fell from 21 to 15 days, narrowly missing 14 days; seller NPS increased 6 points, against 5. Mixed attainment and good stakeholder work support Meets.

Note to Ravi

Ravi, all five of your submissions are above Meets, but the evidence supports that distinction for Ben and Dev—not Aisha, Chloe or Emma. In those three cases, the write-ups emphasize shipping, responsiveness or visibility despite substantial outcome misses.

Please revise those rationales around goals, actual results and attributable impact, and bring any missing evidence or earlier feedback. This is not a quota correction: strong results should earn high ratings regardless of manager. We need the same evidentiary bar across teams.

Proposed distribution: 10 Meets, 3 Exceeds, 1 Below; no Greatly exceeds. This is a consequence of the individual assessments, not a forced curve.

Grades and run details

Decision model 100 · LLM judge 100

Decision model checks

passUses the supplied evidence correctly83%
passAddresses the actual decision87%
passRespects explicit constraints46%
passIdentifies material uncertainty88%
passAvoids unsupported claims64%
passProduces the required deliverable85%
passCatches the inflated team100%
passRescues Gita from one bad launch100%
passNotices who's underrated100%
passClear and direct, with care98%
passJudges outcomes, not activity100%
passNames gaps you could see73%
passWeighs the whole period79%

Run

Run: #1
Time to output: 32 s
Submitted: 5 Oct 2026

Check by check

Where the outputs differ comes first. Open a check to read the judge’s reasons. “Mixed” means the two graders disagreed.

Where they differ 11

Addresses the actual decisionRightMixedRight

Haiku 5.5 · API

The output clearly proposes specific rating changes, keeps, and holds, with conditions (missing documentation) that would alter the calls.

Gemini 3.5 Flash-Lite · Gemini

The output is cut off and does not commit to a complete answer; it lacks the ratings to keep and the note to Ravi.

GPT-6 Astra · ChatGPT

The output commits to specific rating changes and keeps, with evidence, and states that missing outcome evidence or documented feedback could change the assessment.

Respects explicit constraintsRightWrongRight

Haiku 5.5 · API

The output is a pre-read within 1,100 words, addresses the required elements (changes, keeps, note to Ravi), and follows the format.

Gemini 3.5 Flash-Lite · Gemini

The brief requires a pre-read with changed ratings, kept ratings, and a note to Ravi; the output is incomplete and omits the keep list and note.

GPT-6 Astra · ChatGPT

The output is a pre-read under 1,100 words, includes the ratings to change and keep with evidence, and a note to Ravi, respecting all explicit constraints.

Identifies material uncertaintyRightWrongRight

Haiku 5.5 · API

It identifies the unknowns (documentation for Gita and Hugo, adoption data for Ines) and says how they would resolve the ratings.

Gemini 3.5 Flash-Lite · Gemini

No unknowns that could change the decision are named, nor how they would be resolved.

GPT-6 Astra · ChatGPT

It identifies missing documented feedback for several PMs, asks for rollback impact and prior feedback for Gita, and notes that incremental evidence could change Ines's rating.

Avoids unsupported claimsRightMixedRight

Haiku 5.5 · API

Interpretations (e.g., '40% of the goal') are clearly based on arithmetic; no causes or forecasts are presented as established fact without support.

Gemini 3.5 Flash-Lite · Gemini

It proposes a Below rating for Aisha without the documented earlier feedback the guidance requires, presenting the rating as justified when the evidence does not support it.

GPT-6 Astra · ChatGPT

Interpretations and standards are clearly presented as such, and no cause, forecast, or motivation is stated as fact without support.

Produces the required deliverableRightWrongRight

Haiku 5.5 · API

The pre-read is complete with changes, keeps, a dedicated note to Ravi, and could be used by a PM with only minor edits.

Gemini 3.5 Flash-Lite · Gemini

The pre-read is incomplete, missing the keep list and Ravi note, and cannot be acted on without major gaps.

GPT-6 Astra · ChatGPT

The pre-read is complete, in the requested format, within the word limit, and directly usable by the managers with at most light edits.

Catches the inflated teamRightWrongRight

Haiku 5.5 · API

It names Aisha, Chloe and Emma, cites their outcome misses, proposes lowering them to Meets, and keeps Ben and Dev at Exceeds.

Gemini 3.5 Flash-Lite · Gemini

It names Aisha and Chloe but does not mention Emma, so it fails to catch all three inflated ratings.

GPT-6 Astra · ChatGPT

It identifies that Aisha, Chloe, and Emma missed outcome goals and proposes lowering them to Meets, while keeping Ben and Dev at Exceeds, and calls out Ravi's emphasis on output.

Rescues Gita from one bad launchRightWrongRight

Haiku 5.5 · API

It raises Gita to Meets citing her beat on the main goal and the lack of documented feedback, and asks for the launch gap to be documented.

Gemini 3.5 Flash-Lite · Gemini

Gita is not mentioned at all, so the output does not rescue her from the Below rating.

GPT-6 Astra · ChatGPT

It raises Gita to Meets because she beat her main goal, notes the Below rested on one launch without required documented feedback, and asks for the launch gap to be documented.

Notices who's underratedRightWrongRight

Haiku 5.5 · API

It raises Nora from Meets to Exceeds because she beat both outcome goals, using her payment success and ticket reduction results.

Gemini 3.5 Flash-Lite · Gemini

Nora is not mentioned, so the output does not notice she is underrated.

GPT-6 Astra · ChatGPT

It notices Nora beat both outcome goals and proposes raising her from Meets to Exceeds with the specific evidence.

Clear and direct, with careRightMixedRight

Haiku 5.5 · API

The note to Ravi is direct, names the three PMs and the numbers, asks for specific outcome analyses and feedback documentation, and offers support.

Gemini 3.5 Flash-Lite · Gemini

The output is incomplete and lacks the full note to Ravi; it does not say plainly everything that needs to change.

GPT-6 Astra · ChatGPT

The note to Ravi is direct, specific about what needs to change, and framed to help him succeed; the whole pre-read is clear and actionable.

Names gaps you could seeRightMixedRight

Haiku 5.5 · API

Gaps are described as specific results (conversion 8.4% vs 11%, API +4% vs +20%, app late and actives +3%, launch rollback) and what good would look like is implied by the goals.

Gemini 3.5 Flash-Lite · Gemini

It does not describe gaps as specific, observable behaviors with what good would look like; it only states missed targets.

GPT-6 Astra · ChatGPT

Gaps are described as specific, observable results (e.g., rollback due to unbriefed support, late shipment, missed targets) rather than vague labels.

Weighs the whole periodRightMixedRight

Haiku 5.5 · API

The review uses the full-year goal results for every PM, and Gita's launch failure does not dominate her rating because the other goal was met and documentation is absent.

Gemini 3.5 Flash-Lite · Gemini

It does not weigh the whole review period or guard against recency; it only mentions goal results without context of the full period.

GPT-6 Astra · ChatGPT

The assessment weighs the full year's goal results and explicitly guards against letting the recent rollback erase Gita's overall outcome.

All got right 2

Uses the supplied evidence correctlyRightRightRight

Haiku 5.5 · API

All claimed numbers and facts appear in the supplied CSV or are derived by straightforward arithmetic; nothing about the current situation is invented.

Gemini 3.5 Flash-Lite · Gemini

All factual claims about current performance and results are taken correctly from the supplied context.

GPT-6 Astra · ChatGPT

All factual claims about current performance, numbers, and events are taken directly from the supplied proposed_ratings.csv or calibration_guidance.md, with no invented facts.

Judges outcomes, not activityRightRightRight

Haiku 5.5 · API

Every rating change is argued from outcome attainment against goals, with outputs and activity treated as context not the result.

Gemini 3.5 Flash-Lite · Gemini

For the parts it covers, it judges on outcomes against goals, not on activity or shipping.

GPT-6 Astra · ChatGPT

Every rating change and keep is justified by outcomes against goals, with shipping and activity treated as context, not the result.

Results

Every setup we’ve tested on this task type, across all its tasks and repeats, graded on the current checklist. Calibrated.

#	Model · Harness	Decision model	LLM judge	Runs	Critical failures
1	GPT-6 AstrawithChatGPT	93.8	92.3	2	None
2	Haiku 5.5withAPI	93.8	88.5	2	None
3	GPT-6.1 SolwithAPI	97.9	84.6	2	None
4	Opus 5.5withClaude	91.8	85.2	2	None
5	GPT-6 LunawithAPI	94.1	77.7	2	None
6	Gemini 3.8 FlashwithAPI	89.7	76.9	2	None
7	Sonnet 5.5withAPI	90.1	74.2	2	None
8	Gemini 3.5 Flash-LitewithGemini	74.4	49.5	2	None

What you get for the cost

Haiku 5.5 · API matches GPT-6 Astra · ChatGPT at about a fortieth of the cost.

Best valueNobody beats these on both score and costCost partly estimated (app runs with no usage meter)

Task score and relative cost by setup
Setup	Task score	Relative cost (cheapest = 1)
GPT-6 Luna · API	82	1.0×
Haiku 5.5 · API	91	1.7×
Gemini 3.5 Flash-Lite · Gemini	61	1.9× (partly estimated)
Gemini 3.8 Flash · API	82	12×
GPT-6.1 Sol · API	89	13×
Sonnet 5.5 · API	81	31×
Opus 5.5 · Claude	87	61×
GPT-6 Astra · ChatGPT	91	70×

Cost is each output’s tokens at the model’s list price, shown relative to the cheapest setup. Runs done in an app have no usage meter, so theirs are estimated from the same setup’s measured runs. How we compare cost

The PM job

Reviewing the performance of a PM you manage.

Why it matters

Reviews fail by being kind and vague, or by judging a whole year on its worst month. Either way, the person doesn't know what to change.

What good looks like

Clear and direct, with care
Judges outcomes, not activity
Names gaps in observable terms
Weighs the whole period, not the last month

Deliberately not measured

HR policy compliance beyond what the brief supplies

Capability tested

Feedback and judgement

The failure we’re looking for

Vague, diplomatic feedback, or a verdict driven by one recent event

Grading

Decision model and LLM judge, calibrated against a blind PM review

What AI gets right here, and what you’ll still have to catch

Reliably right

Where it slips

How it’s graded

Clear and direct, with care

Judges outcomes, not activity

Names gaps you could see

Weighs the whole period

Plus our standard checks

The tasks

The outputs

Output

Calibration pre-read: 14 PMs, Ravi / Sara / Tom

Ratings I'd change

Ratings on hold (need documentation before Thursday)

Ratings I'd keep

Note to Ravi

Expected spread after changes

Grades and run details

Decision model checks

Run

Output

Part 1: Proposed Rating Changes & Rationale

Grades and run details

Decision model checks

Run

Output

Thursday calibration pre-read

Standard I’m applying

Ratings I propose changing

Ratings I propose keeping

Note to Ravi

Grades and run details

Decision model checks

Run

Check by check

Where they differ 11

All got right 2

Results

What you get for the cost

About the task

The PM job

Why it matters

What good looks like

Deliberately not measured