Which AI builds the best spreadsheets? Vote and shape the benchmark.
Joined January 2026
- Tweets 10
- Following 0
- Followers 80
- Likes 24
8 Photos and videos
Pinned Tweet
Feb 13
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. 🧵
2
5
36
19,655
Feb 21
⚔️BREAKING: Gemini 3.1 Pro Preview debuts as #7 overall on Spreadsheet Arena, trailing Gemini 3 Pro by @GoogleDeepMind which currently stands at #6
8
219
Feb 18
⚔️BREAKING: Claude Sonnet 4.6 by @AnthropicAI debuts at #2 in Spreadsheet Arena, trailing Opus 4.6!
1
8
543
Feb 17
Sonnet 4.6 is now on Spreadsheet Arena!
How well can it model Anthropic's Series G?
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.
1
9
1,165
Feb 14
⚔️BREAKING: Claude Opus 4.6 by @AnthropicAI debuts at #1 in Spreadsheet Arena, surpassing Opus 4.5!
2
22
1,694
Feb 13
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. 🧵
2
5
36
19,655
Feb 13
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.
1
7
603
Feb 13
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 spreadsheetarena.ai
Read the paper at meridian.ai/blog/all/spreads…
@srkundurthy @claranahhh @Zachkirshner @calvincbzhang @ManasiSharma_ @jhnling
1
1
10
724