StarZero All shows Try the podcast clipper →

Anastasios Angelopoulos

Co-Founder and CEO, Arena · 2 appearances on the record.

computed by AI from the episodes · how this works → · full disclaimer →

founderexecutivescientistauthor@ml_angelopoulos ↗LinkedIn ↗angelopoulos.ai ↗

He co-founded Arena, the crowdsourced human-preference benchmarking platform for AI foundation models originating out of UC Berkeley. A former UC Berkeley postdoctoral researcher, he specializes in reliable AI and conformal prediction.

28statements → 15claims → 7claims resolved → 86%fully supported → 3.82/5average certainty → 1.79/5average debate potential → 5said about them ↓

6 supported 1 partly supported 0 contradicted 8 not checkable as stated how the 15 claims stand · each chip opens the sources

1 prediction · 14 assertions · 2 opinions · 3 insights · 8 disclosures · every statement was checked. The prediction and assertions are the 15 claims: statements the public record can support or contradict. 7 are resolved, and 8 name no date, number or outcome precise enough to check. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Anastasios argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

Their most notable supported claim

Assertion Supported
Arena sampled open-source models at 60/40, debunking Leaderboard Illusion paper
“But, you know, there, for example said that we were, that we only sampled, like, nine percent open source models and, like, you know, 60%, like, closed source models, and this created a gap between open and closed source. But in reality, we're actually really …”
Anastasios Angelopoulos Dec 31, 2025 ▶ 11:51 [State of Evals] LMArena's $1.7B Vision — Anastasios Angelopoulos, LMArena

How they sound: not measured why? →

We measure speaking style by listening to the audio itself, and a fair number needs at least 2,000 words from one person on tape we have measured. There is too little of Anastasios Angelopoulos on measured tape to publish a rate. This says nothing about how they speak.

Everything Anastasios Angelopoulos said on Latent Space that made the record, most notable first. Filter by type, assessment or year in the ledger →

Assertion Supported
Angelopoulos: Chatbot Arena scores are calculated via logistic regression
“The arena score that we show on our leaderboard is a particular type of linear model, right? It's a linear model that takes, it's a logistic regression that takes model identities and fits them against human preference, right? So it regresses human preference …”
Anastasios Angelopoulos Nov 1, 2024 ▶ 14:57 In the Arena: How LMSys changed LLM Benchmarking Forever
Assertion Partly supported
Angelopoulos: LMSYS controls for markdown and lists in Arena rankings
“We have, you know, five, six different style components that have to do with markdown headers and bulleted lists and so on that we add here.”
Anastasios Angelopoulos Nov 1, 2024 ▶ 16:24 In the Arena: How LMSys changed LLM Benchmarking Forever
Disclosure
Angelopoulos: LMSYS wants to integrate live code execution in Chatbot Arena
“For example, it'd be great if we could execute code within Arena. It'd be fantastic. We want to do it.”
Anastasios Angelopoulos Nov 1, 2024 ▶ 21:49 In the Arena: How LMSys changed LLM Benchmarking Forever
Disclosure
Angelopoulos: Chatbot Arena is decoupling from LMSYS as co-creators shift focus
“Sort of Chatbot Arena has, of course, like, kind of become its own thing, and Lianmin and Ying, who are, you know, created LMSYS, have kind of, like, moved on to working on SGLang, and now They're doing other projects that are sort of originating from LMSS. An…”
Anastasios Angelopoulos Nov 1, 2024 ▶ 38:23 In the Arena: How LMSys changed LLM Benchmarking Forever

The other half of the tape: Anastasios Angelopoulos's own voice is left out of every number here. Other people bring the name up 5 times in 2 episodes on Latent Space. every mention, with the transcript →

Who brings them up most Anjney Midha 4Shawn Wang 1

Every mention by year

tap a year for its mentions
00214120252026episodesmentions
01120252026episodes it came up in
0020.54120252026episodesmentions per episode
2026 4 mentions in 1 episode
2025 1 mention in 1 episode

Appearances (2)

EpisodeDateSpeaking time
[State of Evals] LMArena's $1.7B Vision — Anastasios Angelopoulos, LMArena Dec 31, 2025 14m
In the Arena: How LMSys changed LLM Benchmarking Forever Nov 1, 2024 17m
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more