The European executive reasoning benchmark

EuroExec measures whether frontier models can make the decisions a European C-suite is accountable for, across finance, business, product, and marketing. Every task is authored and blind-scored by domain experts against a written rubric.

This is a sample analysis of n=200 tasks. The full dataset has n=800+ tasks.

Request dataset access Read the methodology

Leaderboard

46 domain experts authored 200 tasks across finance, business, product, and marketing, each with a written grading checklist. Six frontier models answer every task blind; two independent experts score all 1,200 responses against the rubric.

The headline metric is Reward: the share of tasks a model solves, where a solved task scores a mean rubric of at least 3.0/5 and covers at least 60% of the checklist.

Explore the full leaderboard
01 Fable 5
52%
02 GPT-5.5
43%
03 Claude Opus 4.8
30%
04 Gemini 3.1 Pro
22%
05 GLM-5.2
20%
06 Mistral Large
12%

Difficulty

Across all 1,200 responses (2,400 expert scores, two per response):

35%
of tasks are unsolved by every model
47%
mean checklist coverage
94%
of tasks never fully covered by any model
31%
of answers score ≤ 2/5 on Strategic Reasoning
20%
solve rate in Product & Tech, the hardest domain

Explore the dataset

Four pages open the benchmark up in full, from how each item is constructed to a single graded item you can read from prompt to final scores.

Methodology

How it's built

The seven-stage pipeline from an expert's scenario to a double-judged gold record.

Open → Dataset

Composition & reliability

Domain mix, the rubric, checklist depth, and how much two independent experts agree.

Open → Leaderboard

Full model performance

Per-dimension scores, blind rank distribution, and the head-to-head matchup grid.

Open → Sample Item

One item, end to end

An executive scenario, six blind answers, and two experts' scores, blind to revealed.

Open →

Grounded in real European markets

Every task is set in a specific European market, so a correct answer has to reason about that country's regulation and competitive reality, not a generic "Europe". The map shades each market by how often it appears across Round 1 prompts.

Germany 24.6%
Spain 16.8%
France 15.9%
Italy 13.5%
Portugal 6.6%

and 15 more markets, shaded by how often they appear.

0.9% 15.9% 24.6% 0.3% 13.5% 0.9% 1.5% 6.6% 16.8% 1.8% 5.4%

Access the dataset, or contribute to Round 2

The headline results are public. The complete item-level dataset, and a role in the next round, are open to two audiences.

FRONTIER LABS

Full item-level results

The complete per-item breakdown across all 200 items and 6 models, plus private evaluation of your unreleased models on the same gold set, on request.

DOMAIN EXPERTS

Author the next round of tasks

Senior operators in finance, business, product & tech, and marketing: author and grade the scenarios Round 2 is built on.

Request dataset access

Please fill in all fields with a valid work email.

We use your details to share the results and follow up about them. No lists, no spam. Access follows from marcus@sovrano.ai within one business day.

● REQUEST RECEIVED

You're on the list

A reply follows from marcus@sovrano.ai within one business day. What happens next:

  • Labs: the full item-level results across all 200 items and 6 models, plus a private eval of your unreleased models on request.
  • Domain experts: a short note on the authoring process and Round 2's domains.

Round 2 expands the domains and the language coverage. Requests hear about it first.