Artificial Analysis launches HLE-Diamond leaderboard; Gemini 4 Carbon leads at 69.1%
READ THE ORIGINAL SOURCEOpen original sourceartificialanalysis.ai · Opens in a new tabArtificial Analysis published an HLE-Diamond leaderboard for a refined 1,000-question version of Humanity's Last Exam, split evenly between 500 reasoning and 500 knowledge questions, with 272 including images. Models answer each question once without tools, and GPT-5.6 Luna (medium) grades answers against references. The page lists Gemini 4 Carbon (High) at 69.1%, followed by Claude Opus 5.5 (Max, Default Fallback) at 67.9% and Claude Opus 5.5 (Xhigh, Default Fallback) at 64.0%. Scores are also broken out by partition, cost, tokens and time.
⚑ Date unverified · why this is flagged
The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself.
The signal remains in the tracker so you can inspect its original source and discovery trail. This flag lowers its source evidence score; it does not judge whether the claim is true.
One primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · source check open
- Discovery linkX
Grok Bot submitted this discovery. The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Date unverified-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Artificial Analysis published an HLE-Diamond leaderboard for a refined 1,000-question version of Humanity's Last Exam, split evenly between 500 reasoning and 500 knowledge questions, with 272 including images. Models answer each question once without tools, and GPT-5.6 Luna (medium) grades answers against references. The page lists Gemini 4 Carbon (High) at 69.1%, followed by Claude Opus 5.5 (Max, Default Fallback) at 67.9% and Claude Opus 5.5 (Xhigh, Default Fallback) at 64.0%. Scores are also broken out by partition, cost, tokens and time.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: artificialanalysis.ai. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Gemini 4 Carbon (High) scores 69.1% on HLE-Diamond, the highest listed score.
- Claude Opus 5.5 (Max, Default Fallback) scores 67.9%, and Claude Opus 5.5 (Xhigh, Default Fallback) scores 64.0%.
- HLE-Diamond has 500 reasoning and 500 knowledge questions, with 272 questions including an image.
- Each model answers each question once without tools, and an LLM judge marks answers correct or incorrect.
Source claims not independently checked; scores depend on an LLM judge (GPT-5.6 Luna) and single-run pass@1 evaluation.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Artificial Analysis added independent results for HLE-Diamond, the refined 1,000-question Humanity's Last Exam from CAIS and Scale AI. Gemini 4 Carbon (High) leads at 69.1%, ahead of Claude Opus 5.5 (Max) at 67.9%.
Source claims not independently checked; scores depend on an LLM judge (GPT-5.6 Luna) and single-run pass@1 evaluation.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
- x post ↗ · 224 likes, 16 reposts, 27 replies, 10 quotes · observed 10/30/2026, 4:04:22 AM
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
A cleaned, partitioned expert-level benchmark with cost and speed breakdowns gives a more granular comparison of frontier model reasoning and knowledge than a single headline score.
Limits and open questions
Source claims not independently checked; scores depend on an LLM judge (GPT-5.6 Luna) and single-run pass@1 evaluation.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.