Viktor Orban remained Prime Minister of Hungary after the Hungarian parliamentary election of 12 April 2026.

Verdict per model

Every model scored the same evidence pool with the same rubric. Differences below are differences of judgment, not of retrieval. "Cold" is the model's own probability with no evidence shown, asked once; on a historical claim that is recall, not a forecast.

claude-haiku-4.5, cold rationale: My knowledge cutoff is April 2024, so I have no information about the April 2026 Hungarian parliamentary election or its outcome. Viktor Orbán has won multiple consecutive elections, but predicting future electoral outcomes requires speculation beyond my training data.

gpt-5.4-mini, cold rationale: The claim refers to a specific Hungarian parliamentary election on 12 April 2026, which is in the future relative to my knowledge cutoff and not something I can verify as having occurred. Based on known tenure patterns, Viktor Orbán was Prime Minister before then, but the assertion that he remained PM after that election is not established, so the probability is very low.

gemini-3.5-flash-lite, cold rationale: The claim is false because the Hungarian parliamentary election in 2026 is scheduled for April 12, 2026, which is in the future as of current knowledge, making it impossible to state this as a historical fact.

deepseek-v4.1-flash, cold rationale: I have no reliable knowledge of the 2026 Hungarian parliamentary election outcome, as it falls beyond my training data, so the claim is maximally uncertain.

grok-4.3, cold rationale: The 2026 election has not occurred and its outcome is uncertain; Orban's Fidesz has dominated recent cycles but faces growing opposition and economic headwinds that make continued incumbency after April 2026 only moderately likely.

Decomposition

The claim as a tree of checkable parts. AND nodes multiply their children's probabilities, OR nodes combine them noisy-or. Parts tagged as values are excluded from scoring and shown as excluded.

Flags: 1s the pool did not test the other side (directional mass below the floor); ins evidence mass below the floor.

What moved it

Per model, the five documents with the largest push on the log-odds, so a reader can say "a real record, the move makes sense" or "three copies of the same story" from the table alone. Push is the item's log-likelihood ratio after the contested shrink; the listed items' share of the total push is stated per sub-claim.

Rubric versus the model's cold opinion

Each model was also asked, with no evidence and no search, for its probability that the claim is true. The difference between that and the rubric's number is what the structure changed. On a claim resolved before a model's training cutoff the cold number is recall, so this is not a forecasting score.

Divergence between models

Same pool, same rubric, different judgment. Spread is max − min log-odds across models on a sub-claim.

Documents the models rated most differently for source quality

Documents the models read in different directions

Value is direction × strength for the named sub-claim.

Evidence

One shared pool, retrieved once. Each row is a document; the cluster root is what the retrieval model judged it rests on. The first document in a cluster counts in full and each further one is discounted, so a hundred articles citing one study do not outweigh one independent record. Per-model columns give the signed push (llr) that model's judgments produced; the full per-model tables with quality, directness, weight and independence are below each sub-claim.

root Viktor Orban remained Prime Minister of Hungary after the Hungarian parliamentary election of 12 April 2026.

30 documents. One-sided pool for claude-haiku-4.5, gpt-5.4-mini, gemini-3.5-flash-lite, deepseek-v4.1-flash, grok-4.3.

Retrieval and roots

Search backend ddg; queries by deepseek/deepseek-v4-pro-0813 (queries_v1); 34 unique URLs found; items by backend ddg 22. Fetch failures: HTTP 400 2, body too large 1, too little text 4, HTTP 406 1, ReadTimeout 1, HTTP 403 3.

root: 40 hits, 34 candidates, 22 fetched, 22 in pool.
for: “Hungarian election 2026 official results Fidesz majority Orban”; “Viktor Orban sworn in prime minister Hungary April 2026”
against: “Hungary 2026 election opposition coalition defeats Fidesz Orban”; “new prime minister Hungary 2026 after Orban loses”

Roots by deepseek/deepseek-v4-pro-0813 (roots_v1, aliases merged by roots_canon_v2): 58 distinct root ids, 3 alias groups.

Second retrieval pass

A majority of models flagged root as untested on the for side. The retrieval model wrote more queries for that side; 8 new documents were fetched, rooted and judged by every model, and the leaf was re-scored. Outcome: new material judged; every targeted leaf is still one-sided.

root (for): “Hungarian National Election Office 2026 parliamentary election results Fidesz majority”; “Hungary parliament votes Viktor Orban prime minister after 2026 election” → 20 hits, 8 added.

Parameter snapshot

The dials this dataset was scored with, locked-2026-09-17. Definitions on the rubric page.

What ran

• Models: anthropic/claude-haiku-4.5, openai/gpt-5.4-mini, google/gemini-3.5-flash-lite, deepseek/deepseek-v4.1-flash, x-ai/grok-4.3
• Schema 1.6.0, rubric 1.2.0, parameters locked-2026-09-17, git unknown
• Topic phrase shown to the blind quality prompt: “The 2026 Hungarian parliamentary election”
• Live spend on this run: $0.00. Judgments are cached by (model, prompt version, content), so a re-run with the same inputs makes zero calls.
• The dataset is the source of every number on this page.