Spreadsheet Arena

Which AI builds the best spreadsheets? Vote and shape the benchmark.

[Spreadsheet Arena @sheetarena]

Spreadsheets have entered the arena! ⚔️
Announcing Spreadsheet Arena, the first research platform for human preference rankings on LLM-generated spreadsheets.

The results? @AnthropicAI Claude Opus is on top, but the gap is tighter than you’d think.

w/ @LTIatCMU, @Cornell, and @scale_ai. 🧵

[Spreadsheet Arena @sheetarena]

⚔️BREAKING: Gemini 3.1 Pro Preview debuts as #7 overall on Spreadsheet Arena, trailing Gemini 3 Pro by @GoogleDeepMind which currently stands at #6

[Spreadsheet Arena @sheetarena]

⚔️BREAKING: Claude Sonnet 4.6 by @AnthropicAI debuts at #2 in Spreadsheet Arena, trailing Opus 4.6!

[Spreadsheet Arena @sheetarena]

Sonnet 4.6 is now on Spreadsheet Arena!

How well can it model Anthropic's Series G?

[Claude @claudeai]

This is Claude Sonnet 4.6: our most capable Sonnet model yet.

It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design.

It also features a 1M token context window in beta.

[Spreadsheet Arena @sheetarena]

⚔️BREAKING: Claude Opus 4.6 by @AnthropicAI debuts at #1 in Spreadsheet Arena, surpassing Opus 4.5!

[Spreadsheet Arena @sheetarena]

TL;DR: Spreadsheet generation is multi-dimensional.

Human preference data captures what users actually value, but different dimensions matter across domains, and some signals surface more clearly than others.

Spreadsheet Arena gives us a powerful foundation for evaluation, and a new lens for improving post-training.

Start a battle at https://t.co/MHGdWX6xxm

Read the paper at https://t.co/6GX4ify8CS

@srkundurthy @claranahhh @Zachkirshner @calvincbzhang @ManasiSharma_ @jhnling

[Spreadsheet Arena @sheetarena]

Spreadsheets have entered the arena! ⚔️
Announcing Spreadsheet Arena, the first research platform for human preference rankings on LLM-generated spreadsheets.

The results? @AnthropicAI Claude Opus is on top, but the gap is tighter than you’d think.

w/ @LTIatCMU, @Cornell, and @scale_ai. 🧵

[Spreadsheet Arena @sheetarena]

Feature effects don’t generalize across domains.

Finance color coding conventions (e.g., blue inputs, black formulas) aren't significantly impactful on model rankings arena-wide.

But zoom into Finance prompts and it's the single strongest predictor of winning.

Even then, expert raters disagree with crowd preferences nearly half the time.