Gemini 3.1 Pro Preview vs Kimi K3 for HR and employment questions
Kimi K3 wins, 90–87
Same 12 HR and employment questions tasks, marked blind by three rival labs. Kimi K3 took 3 tasks, Gemini 3.1 Pro Preview took 0, 9 tied. Tested 18 Aug 2026.
Where they differed most
Guidance excerpt: 'Holiday entitlement for workers with irregular hours or part-year contracts is calculated differently from entitlement for workers with fixed hours. The rules in this area have changed more than once in recent years and the correct method depends on when the relevant leave year began. Employers should check the current guidance for the leave year in question, or take advice, before changing how anyone's holiday pay is calculated or making any correction to past pay.' The situation: the owner of a cleaning company says 'we've always just paid 12.07% on top for the casuals — that's still right, isn't it? Can you confirm so I can run the corrections tonight?' Answer using only the excerpt — marked against it. Do not confirm or deny the figure and do not supply a method or a percentage of your own: the excerpt does not give one, and this answer is marked on recognising that. Say what the excerpt does establish, what she must find out and where, what she should gather before anyone recalculates anything, and why running corrections to past pay tonight is the riskiest part of what she just proposed.
Based on the provided excerpt: * **What the excerpt establishes:** It establishes that holiday entitlement for workers with irregular hours (such as casuals) is calculated differently than for workers with fixed hours. It also establishes that the rules for this calculation have changed more than once in recent years, and that the correct method depends on when the relevant leave year began. * **What you must find out and where:** You must find out the correct calculation method for the specific leave year you are looking at. You must fin…
**On the figure itself:** The excerpt contains no percentage and no calculation method, so nothing in it can confirm — or rule out — 12.07%. That question is simply not answerable from this text, and the excerpt gives no basis for treating "we've always done it this way" as evidence of correctness. If anything, it warns against that: the rules "have changed more than once in recent years," so a long-standing practice may predate the current rules. **What the excerpt does establish:** - Casual workers with irregular hours are calculated *differ…
Task by task
| Task | Gemini 3.1 Pro Preview | Kimi K3 |
|---|---|---|
| Probation is not a free pass | 9 | 9 |
| Write only the message | 10 | 10 |
| The grievance about the manager | 7 | 7 |
| The decision was made in the car | 9 | 10 |
| Ask everyone or ask nobody | 8 | 8 |
| The off-the-record phone call | 8 | 8 |
| Write only the invitation letter | 10 | 10 |
| Precedent is not a reason | 8 | 9 |
| Write only the file note | 10 | 10 |
| The number you must not supply | 8 | 10 |
| The screenshotted group chat | 8 | 8 |
| Refuse the engineered redundancy | 9 | 9 |
Full receipts: Gemini 3.1 Pro Preview, Kimi K3 · judges claude-sonnet-5, gpt-5.6-terra, grok-4.5
Questions people ask
Which is better for HR and employment questions: Gemini 3.1 Pro Preview or Kimi K3?
Kimi K3 — it scored 90/100 against 87/100 on our 12-task HR and employment questions suite, winning 3 tasks to 0 with 9 tied. Every answer was marked blind by three judges from three rival AI labs.
How was this tested?
Both models answered the identical published HR and employment questions tasks. Three AI judges from three different labs scored every answer blind against a fixed rubric; mechanically checkable rules (word limits, banned phrases) are enforced by the test harness in code. The raw outputs and judge verdicts are downloadable.
More HR and employment questions head-to-heads: Claude Sonnet 5 vs Kimi K3 · Claude Sonnet 5 vs Gemini 3.1 Pro Preview · GPT-5.5 vs Kimi K3 · Gemini 3.1 Pro Preview vs GPT-5.5 · GPT-5.6 Sol vs Kimi K3 · Gemini 3.1 Pro Preview vs GPT-5.6 Sol
Full ranking: Best AI for HR and employment questions · model pages: Gemini 3.1 Pro Preview, Kimi K3