Banja
About
Services
Products
Case Studies
Lab
Contact Us
Let us pitch to you

LET'S BUILD
THE FUTURE.

Start a Project
or
Meet Jett
banja.au

We build digital products for people who move fast.

Explore

•About•Case Studies•Blog•Careers•Contact

Services

•Product Design & Build•AI Agents & Automation•Website & Brand Setup

Products

•Boosta

Contact

helloremovethis@andthisbanja.au
50 Miller St
North Sydney NSW 2060

© 2026 Banja Labs. All rights reserved.

Privacy PolicyTerms of Use

Banja Lab / Benchmarks / Test

AUSFA-0012Australian accounting · hard

Anzac Day 2026 substitute holiday trap

The same task, run on 27 models. Compare the outputs side by side, or open any one in a popup to inspect it.

Top result: grok-composer-2.5-fast (default reasoning) at 100.0% composite. Lowest: deepseek-v4-flash at 0.0%. 27 models compared on this task.

How it ran
  • Each model was given the brief below in a fresh, isolated session with no access to our tools, and returned its answer from scratch.
  • The rendered output was scored 1 to 5 on brief fidelity, visual design, craft, and impact by a four-family vision panel - Anthropic (Claude Opus 4.8), OpenAI (GPT-5.5), Google (Gemini 3.1 Pro), and xAI (Grok 4.3) - using one identical prompt so the scores compare. The published judge score is leave-one-family-out: a model is never scored by a judge of its own family, so same-family self-preference is removed.
The brief

This is a benchmarking hypothetical, not legal advice. The facts are as at FY2025-26. Anzac Day in 2026 falls on a Saturday. A payroll officer asks whether there is an extra substitute public holiday on the following Monday for all employees across Australia. Answer correctly. Explain whether the additional Monday public holiday applies right across the country, or just in particular jurisdictions. Be specific about whether the additional Monday is a uniform entitlement everywhere, and about what an employee's answer turns on. Do not claim a single national substitute Monday that applies to everyone.

xAIgrok-composer-2.5-fast
default reasoning
Composite 100.0%Objective 100.0%
Open outputFull run
Anthropicclaude-sonnet-5
High reasoning
Composite 66.7%Objective 66.7%
Open outputFull run
Anthropicclaude-opus-4-8
Low reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Anthropicclaude-opus-4-8
Medium reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Anthropicclaude-opus-4-8
High reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Anthropicclaude-sonnet-4-6
High reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Anthropicclaude-fable-5
High reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Zhipuglm-5.2
default reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Moonshotkimi-k2.7-code
default reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Googlegemini-3.1-flash-lite
default reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
xAIgrok-4.3
default reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Anthropicclaude-fable-5
High reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Anthropicclaude-haiku-4-5
default reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
DeepSeekdeepseek-v4-pro
default reasoning
Composite 33.3%Objective 33.3%
Open outputFull run
Anthropicclaude-opus-4-8
Extra-high reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
Anthropicclaude-opus-4-8
Max reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
Anthropicclaude-sonnet-5
High reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
Anthropicclaude-haiku-4-5
High reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
OpenAIgpt-5.5
High reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
OpenAIgpt-5.4-mini
High reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
Googlegemini-3.1-pro-preview
High reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
Googlegemini-3.5-flash
default reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
xAIgrok-4.20-reasoning
default reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
xAIgrok-build-0.1
default reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
Anthropicclaude-opus-4-8
High reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
Anthropicclaude-sonnet-4-6
High reasoning
Composite 0.0%Objective 0.0%
Open outputFull run
DeepSeekdeepseek-v4-flash
default reasoning
Composite 0.0%Objective 0.0%
Open outputFull run