●ChaosWatch
New here? Start here →
Evidence inspector

Middle East & North Africa · 2026-06-28

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.

Region
Asia-PacificEuropeMiddle East & North AfricaSub-Saharan AfricaNorth America
Depth profile
shallow
Date
2026-07-122026-07-112026-07-102026-07-092026-07-082026-07-072026-07-062026-07-052026-07-042026-07-032026-07-022026-07-012026-06-302026-06-292026-06-282026-06-272026-06-262026-06-25
Evidence hash
ef784d2c32ffa37f999fda224359bad47471c1d3f0d3a7b4331e562f84f67dd6

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 2026-06-28 was in the prompt.

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 26.0 points of the 0-100 scale.

claude-opus-5
anthropic
68.0
okSevere

Evidence points to active kinetic conflict, with renewed US and Iran strikes lifting oil prices and attacks on a Qatari-linked tanker and container ship signaling maritime escalation alongside an entrenched proxy war involving Iran, Israel, and the US. Counterweights are real but peripheral \u2014 investment inflows into Egypt and Algeria, stable Moroccan risk ratings \u2014 indicating the disorder is concentrated in the Gulf/Levant rather than region-wide collapse.

evidence ef784d2c32ff…prompt p1
gemini-3.1-pro-preview
google
68.0
okSevere

Renewed military strikes between the US and Iran, alongside recent attacks on commercial shipping, significantly elevate the risk of broader regional conflict. However, ongoing foreign investments in North African green energy and stable economic ratings in countries like Morocco prevent a complete regional deterioration.

evidence ef784d2c32ff…prompt p1
deepseek-reasoner
deepseek
62.0
okUnstable

Renewed US-Iran strikes and proxy attacks on shipping indicate active conflict and regional instability, while economic investments and stable country risk ratings in some states temper the severity. The evidence suggests elevated but not critical chaos, with multiple tensions offset by diplomatic and economic activity.

evidence ef784d2c32ff…prompt p1
llama-3.3-70b-versatile
groq
60.0
okUnstable

The region is experiencing instability due to the use of proxy forces by major powers, renewed US and Iran strikes, and the presence of a hidden cattle disease, all of which contribute to an uncertain environment. However, the region is also seeing investment and cooperation, such as Norway's investment in Egypt's green economy and Germany's energy partnership with Algeria, which suggests that the situation is not yet critical.

evidence ef784d2c32ff…prompt p1
claude-haiku-4-5
anthropic
42.0
okElevated

The MENA region shows mixed signals with concerning security tensions—proxy warfare by Iran, Israel, and the US, plus recent attacks on shipping and renewed strikes—offsetting positive economic developments in renewable energy, investment reforms, and regional partnerships. While instability is present and elevated above baseline, the evidence does not indicate imminent widespread conflict or systemic collapse, with several countries maintaining stable ratings and pursuing constructive economic initiatives despite underlying tensions.

evidence ef784d2c32ff…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.