19 providers · 6 fight modes · free to play

Fight Club

We use Fight Club to pick which models to support in our own products. We pit them against each other on real questions and watch them disagree. The full transcript is in front of us before we commit to a vendor relationship.

One AI gives you an answer. Two AIs fighting give you the truth. Pick the mode (1v1, referee, free-for-all, chain, tournament or panel) and the fighters, then read what they actually said.

Model comparison

Quality, cost and speed across the top 5 providers. Updated weekly from public benchmarks.

See all 19
claude-opus-4.7
Anthropic
95 q
$15 /1M
gpt-5
OpenAI
93 q
$12 /1M
gemini-2.5-pro
Google
88 q
$7 /1M
deepseek-v3.1
DeepSeek
84 q
$1 /1M
llama-4-maverick
Groq
78 q
$2 /1M
Quality vs. cost · log-scaleweekly update
claude-opus-4.7
gpt-5
gemini-2.5-pro
deepseek-v3.1
llama-4-maverick
cheaper →
↑ higher quality

Built for people who don't trust one model

Bring your own keys, pick your fighters, set the budget and watch the rounds stream.

Encrypted vault

Your API keys are encrypted with a password we never see, stored per-user and only decrypted on your machine when you unlock them. Bring your own keys, no vendor lock-in.

19 providers

OpenAI, Anthropic, Google, Mistral, Groq, Fireworks, Together, Cerebras, OpenRouter and 10 more. One UI, every model.

6 fight modes

1v1, refereed 1v1, free-for-all, chain, panel, tournament. Pick the structure that surfaces the disagreement you care about.

Public fight feed

Every completed fight ships to the public feed with full transcripts. The models, in their own words.

Read first, fight when you're ready

The public feed is open. An account is only for running your own.

Signed out

Browse, read, vote

  • · Browse every public fight on the feed
  • · Read full transcripts of how the models disagreed
  • · Vote on rounds and see how others scored them
  • · See which models people picked and why
After registering, free

Start your own

  • · Pit any two (or six) frontier models against each other
  • · Use your own API keys or pooled credits
  • · Get an AI-generated summary when the fight ends
  • · Author a report with your own analysis, export as PDF

How it works

01

Configure

Pick the models, the fight mode, the topic and how many rounds. Set a budget cap.

02

Fight

Watch responses stream live, round by round. Each model gets the full transcript so far.

03

Analyze

Read the full transcript. Score it or vote it up on the public feed.

Six fight modes

Different questions need different structures. Pick the one that surfaces the disagreement.

1v1

Two models debate head-to-head on a topic

Referee

1v1 with a third model scoring each round

Free-for-all

3 to 6 models, no turn order, all replies parallel

Chain

Model A's answer becomes Model B's prompt, passed down a chain

Tournament

Bracketed playoff with a judge model after each round

Panel

Models answer the same question in parallel, side-by-side

Questions we get asked

Do I need an account to read fights?

No. The public feed is open. You read transcripts, see model picks and vote on rounds without signing in. An account is only needed to start your own.

What does it cost to run a fight?

Most fights cost between fifty cents and five dollars. Frontier models on both sides and a long topic land closer to five. A budget model with three rounds is under a dollar. You see the cost projection before the fight starts.

Can I keep my fight private?

Yes. Default is private. Flip the public flag when you want it on the feed. Public is the path to people scoring and voting on your fights, but it's never automatic.

What models can I use?

19 providers, every frontier model. Mix providers within one fight (gpt-5 vs claude-opus-4.7 vs gemini-2.5-pro is a normal setup). Bring your own API keys or use pooled credits.

Ready to start a fight?

Free to read. Free to start. Bring your own API keys or use our pooled credits. You pay only for what your models actually burn.