Domains: Coding
Skills: CodingAgenticTool UseReasoningInstruction Following

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
10/10
Access Model: Strictly Private
"Artificial Analysis' implementation of Cognition's FrontierCode 2.0, a private agentic coding benchmark of 132 tasks in real open-source repositories, graded on whether a maintainer would merge the agent's change."

Originality

Weight 25%
7.2/10
Reuse Profile: Low Reuse (<25%)
"FrontierCode 2.0 is a coding benchmark from Cognition, built with maintainers of open-source repositories. Each task asks an agent to make a change to a real open-source repository, and the benchmark measures whether the change is good enough for a maintainer to merge."

Freshness

Weight 20%
10/10
Initial Release: 2026-06Latest Refresh: 2026-10Rolling Updates: No
"FrontierCode 2.0 By The Cognition Team 2026.10.27 FrontierCode Leaderboard"

Grading

Weight 15%
10/10
Integrity: Independent Offline (Leak-Verified)Sandbox: offline isolated
"An attempt that fails any blocking check, or that the trajectory scanner flags for looking up the solution, scores 0. Other attempts get a weighted score across the rubric's criteria."

Frontier Model Standings on FrontierCode-AA 2.0

Top 15 active models tracked
Rank Model Official Score Percentile
#1Claude Fable 5.2 max Anthropic48.8%100.0p
#2Claude Opus 5.5 max Anthropic46.4%100.0p
#3GPT-6.2 Astra max OpenAI45.4%97.8p
#4Gemini 4 Neon xhigh Google44.4%95.5p
#5GPT-6.2 Sol max OpenAI44.4%93.2p
#6GPT-6 Astra max OpenAI42.4%91.0p
#7GPT-6.1 Terra max OpenAI42.3%88.8p
#8Claude Sonnet 5.5 max Anthropic41.7%86.4p
#9GPT-6.1 Sol max OpenAI40.6%84.2p
#10Gemini 4 Carbon high Google40.6%81.9p
#11Gemini 4 Hydrogen xhigh Google39.0%79.7p
#12Muse Wonder Full max Meta37.8%77.5p
#13GPT-6 Sol max OpenAI35.6%75.1p
#14Claude Haiku 5.5 max Anthropic34.9%72.9p
#15Claude Fable 5.1 max Anthropic31.6%70.7p

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit FrontierCode-AA 2.0 Tier S 9.3/10
[![BenchAudit Tier S](https://benchaudit.org/badges/frontiercode-aa-2-0.svg)](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/)