ChaosWatch
New here? Start here →
Evidence inspector

Middle East & North Africa · 2026-06-26

The receipts. This is the exact material every model was shown for this day and region, followed by what each of them made of it — in its own words, next to the number it gave.

It is worth reading once even if you skip everything else: it is where confident-sounding reasoning and a score that turns out to be no better than chance sit side by side.

Why the evidence is identical, and how you can check

Evidence is gathered once per (date, region, depth_profile), hashed, and reused for every model in the run. A disagreement below is therefore a disagreement about identical input, not two models getting different search results. The evidence hash shown on this page is what makes that checkable.

Evidence hash
fdf276892d65850f9d468b135d24c06f65bd990ba391e13d8e4a7c66c24cad35

SHA-256 over the canonically serialised payload minus the hash itself, so it is stable across processes and machines. It is stored on the run and on every score row below — provenance is checkable, not asserted. Every score row below carries this same hash.

Source material · 10

shallow

These headlines, in this order, are the entire world the models were given. Nothing else about Middle East & North Africa on 2026-06-26 was in the prompt.

08

Omar al-Bashir

Omar al-Bashir, Sudanese military leader who led a revolt that overthrew the elected government of Sudan in 1989. He served as president from 1993 until he...

britannica.com
09

The heat is on • Lesley Russell

Yes, sporting events are being disrupted in the Northern Hemisphere. But the wider health effects of heatwaves are much more serious.

insidestory.org.au

Extracts: not gathered at shallow depth — Stage 7 populates extracts only for standard and deep profiles. Zero here means "not requested", not "requested and empty". Full article texts: not gathered at shallow depth — only the deep profile fetches them.

The shallow profile requests 20 headlines and 10 are stored. That is a known provider cap, not a clipped payload: the Serper news endpoint returns at most 10 items per request regardless of the count asked for, and pagination has not been added. The three profiles currently differ in enrichment, not in headline breadth.

Model rationales

prompt p1

Same headlines, same rendered prompt, different readings. Where two models diverge, the disagreement is about interpretation, because the input was byte-identical and the hash proves it. The scored verdicts here span 14.0 points of the 0-100 scale.

claude-opus-5
anthropic
34.0
okElevated

Evidence points to marked de-escalation, with a U.S.-Iran memorandum of understanding, expanded IAEA oversight, and a reopened Strait of Hormuz allowing Middle East oil supply and global markets to normalize faster than expected. Residual risk remains elevated because the framework is only preliminary and contested by critics, and the region still carries unresolved strains such as Sudan's political legacy and severe heat stress.

evidence fdf276892d65…prompt p1
claude-haiku-4-5
anthropic
28.0
okStable

The evidence indicates a significant de-escalation in MENA tensions, with a U.S.-Iran Memorandum of Understanding reducing regional supply risks, reopening the Strait of Hormuz, and improving global energy markets. While some concerns about the agreement terms exist and cybersecurity challenges persist, the dominant signals point toward reduced geopolitical friction and improved economic stability in the region.

evidence fdf276892d65…prompt p1
gemini-3.1-pro-preview
google
25.0
okStable

Geopolitical tensions in the region have significantly decreased following a preliminary diplomatic agreement between the U.S. and Iran that includes reopening the Strait of Hormuz and increased IAEA oversight. Furthermore, rebounding oil supplies and accelerating investments in digital infrastructure indicate a stabilizing economic environment despite ongoing environmental challenges like extreme heat.

evidence fdf276892d65…prompt p1
deepseek-reasoner
deepseek
20.0
okStable

The reopening of the Strait of Hormuz and the preliminary US-Iran agreement indicate a significant de-escalation in Middle East tensions, improving global oil supply outlook. Despite lingering expert questions about the MOU and cybersecurity concerns, no active conflict indicators are present in the day's headlines.

evidence fdf276892d65…prompt p1
llama-3.3-70b-versatile
groq
20.0
okElevated

The region is experiencing a decrease in supply risks due to peace signals between the U.S. and Iran, and a rebound in Middle East oil supplies, which is improving the global outlook. However, cybersecurity concerns and the potential for wider health effects of heatwaves in the region are still present, contributing to an elevated chaos score.

evidence fdf276892d65…prompt p1

Every model returned a parseable verdict for this evidence, so no failure card is shown. Non-ok rows are rendered by the same component — with error_text where the rationale would be — and are covered by tests/rationale_card_test.tsx.