Claim

Model ledger-default@0.1.0 ledger-strict@0.1.0 ledger-default@0.2.0 ledger-strict@0.2.0 ledger-default@0.3.0 (default) ledger-strict@0.3.0 Snapshot seq

Topics

AI · 1efd24fe Prices and inflation · 1efd24fe

Assessment

Why?

Strongest counted support: The Decoder reports a 62.7% Astra score on ARC-AGI-3 and a test cost of roughly $26,000. weight 1.800000 evidence

Suppressed as dependent: The passage directly states Astra reached 62.7 percent on ARC-AGI-3 at a roughly $26,000 test cost.

Review gaps: qualifiers reviewed, opposing search done, independence reviewed, primary source reviewed

What would most change this: One independent, direct measurement that contradicts this claim would move it from Supported to Unresolved.

Show calculation

Your view

Registered views

Checked as part of

Statements this claim was broken out of. The claim is scored on its own; a statement's reading only counts its claims.

• “The Decoder reported that GPT-6 Astra reached 62.7% on ARC-AGI-3 at a test cost of roughly $26,000.” · 1 claim · 28 September 2026

Evidence for

• The Decoder reports a 62.7% Astra score on ARC-AGI-3 and a test cost of roughly $26,000.

  From Benchmarks disagree on GPT-6 Astra, but its human-beating efficiency on ARC-AGI-3 pulls Chollet’s AGI forecast forward Read 2026-09-28 Relevance DIRECT Steps 0 Counted

  The excerpt directly states both the benchmark score and approximate test cost, with attribution to the report.

• The passage directly states Astra reached 62.7 percent on ARC-AGI-3 at a roughly $26,000 test cost.

  From Benchmarks disagree on GPT-6 Astra, but its human-beating efficiency on ARC-AGI-3 pulls Chollet’s AGI forecast forward Read 2026-09-28 Relevance DIRECT Steps 0 Counted

  Exact quoted passage covers both the score and approximate cost.

Evidence against

None.

Qualifications

• The passage gives 62.7% and roughly $26,000 but omits the test date, exact configuration, denominator, sampling rules, and cost components.

  From Benchmarks disagree on GPT-6 Astra, but its human-beating efficiency on ARC-AGI-3 pulls Chollet’s AGI forecast forward Read 2026-09-28 Relevance DIRECT Steps 0 Counted

  The numerical result is materially narrowed by unspecified benchmark configuration and cost accounting.

• ARC Prize reports 62.7% for the Standard harness but 99.9% for a Provider Adapter harness, so the score and cost require a harness qualifier.

  From OpenAI’s GPT-6 Astra on ARC-AGI-3 Read 2026-09-28 Relevance STRONG Steps 0 Counted

  This does not negate the Standard-harness result, but it opposes treating 62.7% and roughly $26,000 as the model’s unqualified ARC-AGI-3 result.

Suppressed as dependent

Evidence	Group	Kept instead
a1b8482e		788df9ba

Inferences

Concluded from

None.

Used as a premise in

None.

An inference is interpretation, not evidence: it never changes the assessment of its conclusion. Each premise is a claim with its own evidence.

Threads

None. Threads are for disagreements about how a determination was made — a statement whose figures are not in the passage it rests on, two sources that may share an origin. Something about the world belongs in the evidence above.

Claim edges

None. Edges are stored and displayed; v0.1 does not propagate probability across them.

Review checklist

Review checks: 0 of 4

3 checks by this claim's own author. No independent review yet. 1 OPPOSING EVIDENCE SEARCH · 1 QUALIFIER CHECK · 1 EVIDENCE VERIFICATION. A check by the person who recorded a claim does not raise its review coverage.

Check	Done	By
qualifiers reviewed	no
opposing search done	no
independence reviewed	no
primary source reviewed	no

Summary

Contribution history

seq	event	detail
12391	APPENDED
12392	ACCEPT	AUTOMATIC_AFTER_VALIDATION
12397	LINK_EVIDENCE	by 1efd24fe (accepted)
12399	TASK_RESULT	by 1efd24fe (accepted)
12412	TASK_RESULT	by 1efd24fe (accepted)
12629	TASK_RESULT	by 1efd24fe (accepted)