Will an AI model score at least 90% on the FrontierMath Benchmark before 2027? [ resolves 2026-12-31 (211D) ]

AI model scores ≥ 90% on FrontierMath Benchmark before 2027?

polymarket: [C] multiple sources, no tie-break·reporting consensus methodology ›

markets · by resolution date

polymarket 1 market

market	resolves	P(YES)		vol (24h)	vol (cum)		RCG	venue id
≥ 90%	2026-12-31	22.0%		—	$75K		C	`0x4632e9…341b`

resolution architecture

venue	proposer	source	citation	arbitration	class	analyst notes
polymarket	`Whitelisted Proposers`	uncommitted	not provided	`Optimistic Oracle (UMA)`	`Other`	—

verbatim rules

polymarket 1 market · share this text

This market will resolve to "Yes" if a state-of-the-art (SOTA) AI model achieves a score of 90% or greater on the FrontierMath Exam by December 31, 2026, 11:59 PM ET. Otherwise, the market will resolve to "No". The primary resolution source will be information from EpochAI however a consensus of credible reporting may also be used.

platform source field polymarket.resolutionSource → ∅ no committed source — see rules text above

recent wire items

monitoring status: active no active wire

No CM Signal wire has been published for this event yet.

CM Signal’s news-cycle scan surfaces the day’s top stories alongside the prediction markets pricing them. When a story references this event, its wire is published here and links back to this page.

programmatic access · four surfaces, same payload

AI grounded search reads embedded JSON-LD in HTML. Developers query REST. Agentic AI clients (Claude Desktop, Cursor) call MCP tools. AI crawlers index via /llms.txt. Same canonical record at every surface.

HTML	browsers, AI grounded search, crawlers (embedded JSON-LD `@type: Dataset`)	`https://clearmarket.fyi/events/ai-model-scores-90-on-frontiermath-benchmark-before-2027/`
JSON	REST API for developers	`https://api.clearmarket.fyi/v1/events/ai-model-scores-90-on-frontiermath-benchmark-before-2027.json`
MCP	agentic AI tool call (Claude Desktop, Cursor, Continue)	`clearmarket.get_event("ai-model-scores-90-on-frontiermath-benchmark-before-2027")`
AGENT	AI crawler discovery index	`/llms.txt`

 Snapshot 2026-06-03. Venue data via Kalshi + Polymarket APIs. Editorial fields (tags, editorial_notes) are ClearMarket-drafted with AI assistance under editorial review. Derived fields (venues_covered, resolution_clarity_grade, rcg_score) computed at serve time. Full per-field map in the JSON record under field_provenance.
  raw JSON record · same payload returned by REST endpoint
 {
  "event_id": "CM-EVT-TJHL5Z0RK9",
  "slug": "ai-model-scores-90-on-frontiermath-benchmark-before-2027",
  "question": "Will an AI model score at least 90% on the FrontierMath Benchmark before 2027?",
  "category": "technology",
  "tags": [
    "technology",
    "ai",
    "machine-learning",
    "benchmark-performance",
    "mathematical-reasoning",
    "2026"
  ],
  "venues_covered": [
    "polymarket"
  ],
  "market_count": 1,
  "cumulative_volume_usd": 75304,
  "resolution_clarity_grade": "C",
  "rcg_score": 40,
  "rcg_caps": [
    "multi_source_no_conflict_rule"
  ],
  "resolution_source": null,
  "resolution_source_url": null,
  "arbitration_model": "uma_oracle",
  "proposer_model": "managed_whitelist",
  "field_provenance": {
    "question": {
      "source": "clearmarket_editorial"
    },
    "tags": {
      "source": "clearmarket_editorial",
      "ai_drafted": true
    },
    "resolution_clarity_grade": {
      "source": "derived",
      "method": "rcg_v2_7factor"
    },
    "venues_covered": {
      "source": "derived"
    }
  }
}

snapshot 2026-06-03T14:52:43.794845+00:00 schema v0.2.0-universe all events →