Will OpenAI achieve a score above 50% on Humanity's Last Exam by 2026? [ resolves 2026-12-31 (149D) ]
polymarket: [B] single source·objective outcome methodology ›
distribution · by strike · marks: daily snapshot
polymarket 5 markets
resolution architecture
| venue | proposer | source | citation | arbitration | class | analyst notes |
|---|---|---|---|---|---|---|
| polymarket | Whitelisted Proposers | not provided | not provided | Optimistic Oracle (UMA) | Other | — |
verbatim rules
polymarket
This market will resolve to "Yes" if any model published by OpenAI achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.
The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".
platform source field
polymarket.resolutionSource → ∅ none returned sources (1) · stated precedence rule
- agi.safe.ai source of record venue-listed
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
One canonical record at every surface — embedded JSON-LD, REST, MCP, and /llms.txt.
| HTML | browsers, AI grounded search, crawlers (embedded JSON-LD @type: Dataset) | https://clearmarket.fyi/events/highest-openai-score-on-humanitys-last-exam-in-2026-20260723225144062/ |
| JSON | REST API for developers | https://api.clearmarket.fyi/v1/events/highest-openai-score-on-humanitys-last-exam-in-2026-20260723225144062 |
| MCP | agentic AI tool call (Claude Desktop, Cursor, Continue) | clearmarket.get_event("highest-openai-score-on-humanitys-last-exam-in-2026-20260723225144062") |
| AGENT | AI crawler discovery index | /llms.txt |
Snapshot 2026-08-04. 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-NMKP6F3908",
"slug": "highest-openai-score-on-humanitys-last-exam-in-2026-20260723225144062",
"question": "Will OpenAI achieve a score above 50% on Humanity's Last Exam by 2026?",
"category": "technology",
"tags": [
"technology",
"ai",
"openai",
"benchmarking",
"language-models",
"2026"
],
"venues_covered": [
"polymarket"
],
"market_count": 5,
"cumulative_volume_usd": 22281,
"resolution_clarity_grade": "B",
"rcg_score": 77,
"rcg_caps": [],
"resolution_source": null,
"resolution_source_url": "https://agi.safe.ai/",
"source_status": "platform_named",
"source_of_record": "agi.safe.ai",
"resolution_source_list": [
{
"name": "agi.safe.ai",
"url": "https://agi.safe.ai/",
"provenance": "platform_api"
}
],
"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"
}
}
}