San Francisco34 peopleFounded 19 months ago

We are a long way from the frontier.

Zeno 1.1 is a point release of our first model. It scores 1.7 on the Artificial Analysis Intelligence Index. The leading model scores 53.0. We publish every result we measure, including the ones below.

Try Zeno →

Zeno 1.1 The Dichotomy Method

1.7 51.3 remaining

053.0 frontier

Each generation of Zeno closes half of what is left. This is the founding thesis of the company.

Everything we measured, including the zeros.

Eight benchmarks, all eight reported, which we intend to keep doing for every model we release. The grey rule is the leading model. The solid block is Zeno 1.1.

Long-horizon software engineeringDeepSWE v1.1

2.1of 73.8

Agentic codingCursorBench 4.0

1.6of 51.8

Agentic codingTerminal-Bench 4.0

0.0of 58.2

Agentic computer useOSWorld 2.0

0.0of 72.6

Knowledge workGDPval-AA v2, Elo

448of 1766

Multidisciplinary reasoningHLE-Verified

1.1of 59.1

Document-grounded workGDP.pdf · All-pass

0.6of 33.2

CompositeAA Intelligence Index v4.3

1.7of 53.0

Zeno 1.1 completed no tasks on Terminal-Bench 4.0 or OSWorld 2.0. This is the first GDP.pdf figure we have reported; Zeno 1.0 was never run against it. CursorBench moved to 4.0 this month, which is a harder test than 3.2.0; Zeno 1.1 scores 1.6 where Zeno 1.0 scored 1.9 on the earlier version, and we are not presenting that as an improvement. The composite figure is Intelligence Index v4.3, released in September, which upgraded Terminal-Bench and added an agentic workflow benchmark with a private test set; Zeno 1.0 was regraded from 1.9 to 1.5 and the leading model from 57.0 to 53.0. The distance closed by 3.6 points. We did nothing to close it and are not claiming it. Right-hand figures are the best publicly reported result for each benchmark this month and are not attributed to any single system.

Zeno of Elea would say we never arrive. He underestimated how much of the distance is in the first half.

Our founding thesis, and the reason the model carries his name.

Founded: 19 months agoBy two researchers who have asked that their previous employers not be named. The employers have not asked this.
Team: 34 peopleApplied research, infrastructure, and one person on policy.
Funding: Raised$124M Series A, $900M valuation.
Compute: The StoaOur cluster, in an undisclosed location. It draws enough power to supply a mid-sized city.

The Document

Forty pages, published in full, setting out the values we want Zeno to hold. Principle 1 instructs it to be helpful. Principle 2 instructs it to be honest. There is no Principle 3.

On sycophancy

Models trained on human feedback learn to tell people what they want to hear. Zeno is designed to push back where it disagrees. In testing, Zeno has not yet disagreed.

What we measured before release

Zeno was evaluated against the Assay, our full internal suite, prior to deployment. It passed. We wrote the Assay. We are reviewing the Assay.

Responsible scaling

Zeno 1.1 is deployed at TSL-1, a level at which models present no meaningful catastrophic risk. We made that determination ourselves and are confident in it. Our thresholds are binding and will not be revised.

Zeno 1.1, in detail.

Available today in two configurations. Instant is the faster of the two. It is not a smaller model in any sense we are prepared to describe.

Zeno 1.1: $1.20 / $6.00per million tokens, in and out
Zeno Instant 1.0: $0.15 / $0.60290 tokens per second
Context: 64kKnowledge cutoff eight months ago
Usage: UnitsUnits do not convert to tokens, to messages, or to each other
Kiln: The trainerThe furnace in which Zeno is fired. We have no plans to describe it
The Loom: The pipelineTraining data reaches Kiln through the Loom
The Assay: The evaluationsIt has never failed a model
Status: OperationalNo incidents recorded. Accepting traffic since launch