# CharXiv Reasoning benchmark · Enso — Hanzo AI

> CharXiv Reasoning: every model with a score, each row naming who measured it. Enso is the router, so its row is the pool it chose from.

[Benchmarks](https://hanzo.ai/benchmarks) / [Enso](https://hanzo.ai/benchmarks?product=Enso#all) / CharXiv Reasoning

Enso · Model board

# CharXiv Reasoning

CharXiv Reasoning: every model with a score, each row naming who measured it. Enso is the router, so its row is the pool it chose from.

## Latest

[85.5%Score · Enso Ultrao3, CharXiv official leaderb… 78.6% · Win · snapshot of Aug 16, 2026 · Hanzo-measured](#history)

[78.0%Score · Enso Proo3, CharXiv official leaderb… 78.6% · Loss · snapshot of Aug 16, 2026 · Hanzo-measured](#history)

## History

2 results, newest first. Superseded runs stay, so a revision's progress can be read.

Measured

Subject

Metric

Value

Baseline

Result

Status

snapshot of Aug 16, 2026

Enso Ultra

Score

85.5%

o3, CharXiv official leaderb… 78.6%

Win

Frozen · Hanzo-measured

snapshot of Aug 16, 2026

Enso Pro

Score

78.0%

o3, CharXiv official leaderb… 78.6%

Loss

Frozen · Hanzo-measured

## The whole board

Every model with a score, as the leaderboard snapshot holds it. Hanzo-measured and publisher-reported rows are different evidence and are marked apart.

Model

Vendor

Score

Measured by

enso-ultra

Hanzo

85.5%

Hanzo-measured

o3

OpenAI

78.6%

CharXiv official leaderb…

enso

Hanzo

78.0%

Hanzo-measured

gpt-4.1

OpenAI

56.7%

CharXiv official leaderb…

o1

OpenAI

55.1%

CharXiv official leaderb…

gpt-4o-241120

OpenAI

50.5%

CharXiv official leaderb…

gpt-4o-240513

OpenAI

47.1%

CharXiv official leaderb…

## Conditions

7 models on the board2 Hanzo-measured, the rest as their publishers report

## Hardware

The run records no device or host.

## Source

[the leaderboard snapshot (lib/data/leaderboard.json)](https://hanzo.ai/models/enso)

## Reproduce

No public command regenerates this result. The source above is the record it is read from.

## More Enso benchmarks

[GPQA-Diamond](https://hanzo.ai/benchmarks/gpqa) · [LiveCodeBench v6](https://hanzo.ai/benchmarks/livecodebench-v6) · [Humanity's Last Exam](https://hanzo.ai/benchmarks/humanitys-last-exam)

[Every result for CharXiv Reasoning on the shelf](https://hanzo.ai/benchmarks?q=CharXiv%20Reasoning#all) · [How these are measured](https://hanzo.ai/benchmarks#methods)