Changelog

Thinking Machines has released Inkling 2 Small, scoring 31 on the Artificial Analysis Intelligence Index - their plan to release its weights would make it the highest-scoring open weights model developed outside China based on current rankings

Nanbeige has released Nanbeige4.3-33B, an open weights model matching Qwen3.8 27B (xhigh) at 20 on the Artificial Analysis Intelligence Index v5 with stronger terminal use but weaker knowledge

Upgraded AA-LCR-25 to AA-LCR v1.1 and increased repeats from 10 to 25, tightening confidence intervals. Expanded coverage to six open weights models with GLM-5.3 Flash and Muse Spark Open.

Time per Task is the new headline for comparing models. Output Speed now covers the whole request, including the wait for the first token, and averages single-request and multi-turn agentic workloads. Token counts come from each provider's API. Failures on the endpoint's side count against it, and every endpoint shows an Endpoint Error Rate.

Incorporated grading robustness improvements from the CritPt authors and regraded all models on CritPt v2.

Google’s Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5, and second only to Claude Opus 5.5 on the Artificial Analysis Coding Agent Index

itHub has released Copilot Fusion in GitHub Copilot, which orchestrates between Anthropic and OpenAI models. It scores 2 points below Opus 5.5 in Claude Code at half the Cost per Task in the Coding Agent Index

Index v5 features 2 new benchmarks and 3 upgrades. For the first time, the majority of the Index is built on private datasets

New to the Intelligence Index:

➤ FrontierCode 2.0: Cognition’s private benchmark of real-world coding tasks, graded on whether a repository maintainer would merge the agent’s change

➤ Terminal-Bench-Science: 70 agentic scientific research tasks, run in a terminal environment

Upgraded:

➤ HLE-Diamond (replacing Humanity’s Last Exam): a refined 1,000-question version of Humanity’s Last Exam, split evenly between reasoning and knowledge questions

➤ AA-Omniscience v1.1: an updated dataset with saturated questions and all public set questions removed, new questions added, and ambiguous or erroneous questions revised

➤ CritPt v2 (Hard Subset): a private 40-question hard subset of CritPt v2, revised by the CritPt authors and run with a code-execution tool

Staying in the Index: AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0

Removed from the Index: GDPval-AA v2, SciCode and AA-LCR

OpenAI has released GPT-6.1 Terra, pushing the cost efficiency frontier. It is the first Terra-class model since GPT-5.6, and is more intelligent for less than a third of the cost

Artificial Analysis' implementation of HeyGen's Code2Video Bench, evaluating how well models create short product and brand videos from 114 design briefs using HyperFrames HTML.

Kimi K3.1 Pro launches at 4th on the Artificial Analysis Intelligence Index and will lead open weights models