← 2026-W44 Weekly archive
SOURCE RECORD · obs_38934f3779ba…

Artificial Analysis · Industry data source update

Substantive changesRecordedObservation date 2026-10-29(day precision)Revision r2

Summary

AA-Omniscience v1.1 Non-Hallucination Rate

Rule generation

Permanent link

https://daily.maas.click/item/obs_38934f3779ba3f51db3ca03d3bfb4b943253c499a87c67c76f65a8f52222ac9f/

Source page

https://artificialanalysis.ai/ ↗

This link points to the source's official page (not content on this site).

changesExcerpt

The following is an excerpt of the saved changes

Evidence level: source discrepancy (source_diff) — this is a change to the crawled source page; changes in the pricing page text do not represent verified price adjustments.

24 lines added
  • AA-Omniscience v1.1 Accuracy
  • AA-Omniscience v1.1 Non-Hallucination Rate
  • Announcing Artificial Analysis Intelligence Index v5
  • Artificial Analysis Intelligence Index v5.0
  • Artificial Analysis Intelligence Index v5.0 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1
  • Artificial Analysis Progress Index v1, Over Time
  • CritPt v2 (Hard Subset)
  • Each lab’s line shows its highest-scoring model available at that point in time, using each model’s highest-scoring effort variant. Read the Progress Index v1 methodology.
  • For example, an older model might have been tested on easier benchmarks and a newer model on harder ones. Models tested on both sets help us estimate the difference in difficulty and compare the older and newer models on the same scale.
  • FrontierCode 2.0
  • Gemini 4 Carbon (High)
  • Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5
  • GitHub Copilot Fusion orchestrates Anthropic and OpenAI models to balance performance and cost
  • GoogleAnthropicOpenAIMetaKimiDeepSeekAlibabaSpaceXAIZ AIInclusionAIXiaomiStepFunMiniMaxReflectionInstitute of Foundation ModelsThinking MachinesMistral
  • GoogleAnthropicOpenAIMetaKimiSpaceXAIDeepSeekZ AIXiaomiOther Models
  • HLE-Diamond
  • HealthBench and HealthBench Professional: Evaluating models in realistic health conversationsSee more
  • How the Progress Index v1 is calculated
  • Intelligence Index v5
  • Intelligence IndexUpdatedOpen Weights / ProprietaryText Only / Multimodal InputsBy Country
  • Item response theory estimate of general capability across Artificial Analysis evaluations · Highest-scoring effort variant shown
  • Methodology updated · 27 Oct
  • Mistral Large 4 (High)
  • Mistral Large 4 (Medium)
5 lines removed
  • AA-LCR v1.1
  • AA-Omniscience Accuracy
  • AA-Omniscience Non-Hallucination Rate
  • Announcing AA-3D: a benchmark for interactive 3D experiences
  • AnthropicMetaKimiOpenAIGoogleSpaceXAIXiaomiAlibabaDeepSeekZ AIInclusionAIStepFunMiniMaxMistralInstitute of Foundation ModelsReflectionThinking Machines

Revision history (2 versions)

  • r1Initially recorded
  • r2 Changes Updated