Agents run dozens of inference calls per task. Latency compounds. Cost compounds.
We tested Mercury 2 on @pinchbench — the benchmark built on @openclaw, the fastest-growing open-source project in GitHub history.
78% success rate. Fastest in class. Under $1/M tokens.
This is what production agents need 👇
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
If you run AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → loops, a model at 78% success on an agent benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → for under $1 per million tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → changes the cost of the calls between the interesting ones. The numbers are vendor-run, so check them against your own task mix.
