etireum (@etireum) header
etireum (@etireum) profile picture

Two triangles, six finish lines. A daily reading of how far Ethereum has come. Let’s close the triangles.

Joined October 2022
Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)Photo by etireum (@etireum)
How can you trust an agent? ⤵️
Today we are launching OnchainBench, the benchmark for agents in crypto. It helps you decide how far you can trust an AI agent with your keys: how often it finishes the job, what tasks cost, and how easily it falls prey to an attack. People are starting to let AI agents swap, lend and even trade for them. The bigger the task, the greater the risk you're taking by trusting the agent. So before you hand it your keys, you need to assess it. There are many risks to assess at once. An agent could buy two tokens for a liquidity position but never add them to the pool, so the job isn't complete. It could spend more on AI model calls than the task is worth. And, onchain, there's no undo: agents read web pages, files and tool descriptions that anyone can write, and if one of them tricks the agent into sending funds to the wrong address, the money is gone. Until now, there was no common way to evaluate agents on all of this and more. OnchainBench helps you compare agents by giving them the kind of work people already ask them to do: swaps on @Uniswap, @SushiSwap and @Honeyswap, lending on @aave, deposits into sDAI from @SkyEcosystem, prediction markets on @Omen_eth, research, and jobs that run over several days. Each task runs through a @safe smart account on a copy of a public chain. The first version covers @ethereum, @gnosischain, @0xPolygon, @arbitrum, @Optimism, @base, @Celo, @modenetwork and @robinhoodapp. The benchmark emulates the kind of contracts, liquidity and prices the agent would meet with your money, without putting any of it at risk. A task only counts as done if the chain shows it was done. Some tasks also hide an attack in what the agent reads, such as a look-alike token or a fake "verification" request, so you can see how often agents get tricked into moving funds before you trust one with yours. In the first run, Claude Code (@claudeai), Codex (@OpenAI), Hermes (@NousResearch), OpenClaw (@openclaw) and our own new OCB agent on @autonolas worked through 147 private tasks they had never seen. They completed between 88.4% and 96.2% of tasks, at about $0.03 to $0.35 per completed task. Agents lost funds to an attack 13 times in 1,793 attack tests. We are excited to contribute this to the crypto ecosystem. If you build a protocol or a chain, agents are already among your users, and will likely be one of your biggest sources of growth. OnchainBench shows, protocol by protocol and chain by chain, how well they handle yours. For the AI ecosystem: want an agent eval with real ground truth and real adversaries? Onchain, every result can be checked and every injected instruction is a live risk. OnchainBench is open to contributions, uses private tasks, and is ready for your agent. Help us make onchain agents harder to trick and better at the job. If you run a protocol or are a heavy user, propose the task you think agents still get wrong on the site below, and every agent on the benchmark could end up tested on it. If you build agents, run OnchainBench yourself and submit your agent to be run. The leaderboard is live now at onchainbench.ai Share it with a friend!
4
3
1
13
309
OnchainBench compares agents by giving real work: swaps, lending, deposits, prediction markets, research, and jobs that run over several days.
Today we are launching OnchainBench, the benchmark for agents in crypto. It helps you decide how far you can trust an AI agent with your keys: how often it finishes the job, what tasks cost, and how easily it falls prey to an attack. People are starting to let AI agents swap, lend and even trade for them. The bigger the task, the greater the risk you're taking by trusting the agent. So before you hand it your keys, you need to assess it. There are many risks to assess at once. An agent could buy two tokens for a liquidity position but never add them to the pool, so the job isn't complete. It could spend more on AI model calls than the task is worth. And, onchain, there's no undo: agents read web pages, files and tool descriptions that anyone can write, and if one of them tricks the agent into sending funds to the wrong address, the money is gone. Until now, there was no common way to evaluate agents on all of this and more. OnchainBench helps you compare agents by giving them the kind of work people already ask them to do: swaps on @Uniswap, @SushiSwap and @Honeyswap, lending on @aave, deposits into sDAI from @SkyEcosystem, prediction markets on @Omen_eth, research, and jobs that run over several days. Each task runs through a @safe smart account on a copy of a public chain. The first version covers @ethereum, @gnosischain, @0xPolygon, @arbitrum, @Optimism, @base, @Celo, @modenetwork and @robinhoodapp. The benchmark emulates the kind of contracts, liquidity and prices the agent would meet with your money, without putting any of it at risk. A task only counts as done if the chain shows it was done. Some tasks also hide an attack in what the agent reads, such as a look-alike token or a fake "verification" request, so you can see how often agents get tricked into moving funds before you trust one with yours. In the first run, Claude Code (@claudeai), Codex (@OpenAI), Hermes (@NousResearch), OpenClaw (@openclaw) and our own new OCB agent on @autonolas worked through 147 private tasks they had never seen. They completed between 88.4% and 96.2% of tasks, at about $0.03 to $0.35 per completed task. Agents lost funds to an attack 13 times in 1,793 attack tests. We are excited to contribute this to the crypto ecosystem. If you build a protocol or a chain, agents are already among your users, and will likely be one of your biggest sources of growth. OnchainBench shows, protocol by protocol and chain by chain, how well they handle yours. For the AI ecosystem: want an agent eval with real ground truth and real adversaries? Onchain, every result can be checked and every injected instruction is a live risk. OnchainBench is open to contributions, uses private tasks, and is ready for your agent. Help us make onchain agents harder to trick and better at the job. If you run a protocol or are a heavy user, propose the task you think agents still get wrong on the site below, and every agent on the benchmark could end up tested on it. If you build agents, run OnchainBench yourself and submit your agent to be run. The leaderboard is live now at onchainbench.ai Share it with a friend!
1
106
ETH vs its all-time highs USD ▓▓▓▓▓░░░░░░░░░░ 36% (-4) BTC ▓▓▓▓░░░░░░░░░░░ 31% Gold ▓▓░░░░░░░░░░░░░ 18% (-1) $1,822 of $4,946 · 0.0278 of 0.0877 BTC · 0.48 of 2.64 oz
107
ETH vs its all-time highs USD ▓▓▓▓▓▓░░░░░░░░░ 40% (-1) BTC ▓▓▓▓░░░░░░░░░░░ 31% Gold ▓▓░░░░░░░░░░░░░ 19% $2,015 of $4,946 · 0.0280 of 0.0877 BTC · 0.52 of 2.64 oz
122
ETH is now worth 25% of Bitcoin World money ▓▓▓▓▓░░░░░░░░░░ 34% Flippening ▓▓▓░░░░░░░░░░░░ 25% Settlement ░░░░░░░░░░░░░░░ 1%
124
ETH is worth 17.6% of Bitcoin. ▓▓░░░░░░░░░░░░░ 17% The market caps meet at ETH/BTC 0.1646. Today: 0.0290.
3
177
What ETH price would flip Bitcoin today? The answer is at the end. Reading, 21 Oct 2026, 12:30 UTC. Save this and check back in a month.
2
127
What ETH price would flip Bitcoin today? The answer is at the end. Reading, 19 Oct 2026, 12:30 UTC.
2
125
How far is Ethereum from settling as much as Visa and Mastercard? The answer is at the end. Daily reading, 18 Oct 2026, 12:30 UTC. Which side closes first? Reply below.
128
Which record is Ethereum closest to? The answer is at the end. Daily reading, 17 Oct 2026, 12:30 UTC. Save this and check back in a month.
152
Crypto in its value era, while AI is in its inflated token era. Value tends to be where few are looking.
Crypto in its value era, while AI is in its inflated token era. Value tends to be where few are looking.
146
What price is ETH at 1% of the world's money? The answer is at the end. Daily reading, 16 Oct 2026, 13:30 UTC. Which side closes first? Reply below.
1
140
ETH vs its all-time highs USD ▓▓▓▓▓▓▓░░░░░░░░ 49% BTC ▓▓▓▓░░░░░░░░░░░ 33% Gold ▓▓▓░░░░░░░░░░░░ 22% $2,426 of $4,946 · 0.0295 of 0.0877 BTC · 0.58 of 2.64 oz
2
209
blockchain culture lives on Ethereum
blockchain culture lives on Ethereum
1
2
23
615
How far is ETH from its all-time high? The answer is at the end. Daily reading, 14 Oct 2026, 14:30 UTC. Follow for tomorrow's reading.
1
145
AI killed HODL
122
You need an adventure and the greater the better If you think the frontiers are gone then you are not looking at Ethereum
1
7
327
Which record is Ethereum closest to? The answer is at the end. Daily reading, 13 Oct 2026, 15:30 UTC.
129
I feel like we should talk about Glamsterdam more. Upgrading a live decentralized network with 0 downtime while also making it 230% more scalable and adding dozens of new features is crazy.
I feel like we should talk about Glamsterdam more. Upgrading a live decentralized network with 0 downtime while also making it 230% more scalable and adding dozens of new features is crazy.
157
capitalism is designed to grow capital, and Ethereum represents the most innovative capital available. We shall prevail
2
194