Model Arena · depth shallow

Middle East & North Africa · 2026-06-26

Season 1 · 2026-06-25 → 2026-07-12 · 90 region-days (18 dates × 5 regions) · scored 2026-08-05 → 2026-08-06 · closed pilot, not a live feed

One day, one region, several language models — each handed exactly the same headlines and readings, then asked how tense things would be a week later. Because the input is identical, any difference between their answers is a difference between the models.

This page shows what they said. Whether any of it was right is a separate question, answered on the Leaderboard — and the short version there is that none of them detectably beat guessing. Scores run from 0 (calm) to 100 (catastrophe); the Leaderboard puts those scores and what actually happened on one standard scale before comparing them, which is why its error numbers sit around 1 rather than on the 0–100 scale.

How 'identical evidence' is guaranteed

Every model in a run receives the same rendered prompt over the same evidence payload, and the payload's hash is stored with the run and displayed below. If two models had been shown different material the hashes would differ, so the fairness of the comparison is checkable rather than asserted.

Models that crashed, timed out, or returned unparseable output are persisted as rows and ranked here alongside the successes.

Consensus

25.0

the middle of 5 answers, with the highest and lowest set aside

Completion

100.0%

5 scored / 5 attempted — failures stay in the denominator

Evidence

fdf27689…ad35

10 headline(s), shared by every model

Ranking

prompt version p1depth shallow

Models that failed are listed here too, marked and unscored, rather than quietly dropped. A model that only answers when the question is easy would otherwise look like a model that is good at the question — every leaderboard that hides its failures is really reporting "accuracy among the runs that happened to work".

claude-opus-5okElevated

anthropic

latency 14,660 mstokens in 1,318tokens out 255

34.0

claude-haiku-4-5okStable

anthropic

latency 3,451 mstokens in 917tokens out 105

28.0

gemini-3.1-pro-previewokStable

google

latency 8,851 mstokens in 544tokens out 78

25.0

deepseek-reasonerokStable

deepseek

latency 6,271 mstokens in 824tokens out 449

20.0

llama-3.3-70b-versatileokElevated

groq

latency 1,001 mstokens in 771tokens out 91

20.0

Every model in this run returned a verdict, so no failure row is shown.