FrontierCode 2.0 gets harder, average score drops from 45% to 29%
11/14/2026 — 11/14, 09:18·1 sources (all)·1 reports (all)
Key takeaways
- Artificial Analysis reports that all 23 configurations scored lower on FrontierCode-AA 2.0 than on v1.1, with the average dropping from 45%…
Background & analysis
On November 14, 2026, at 08:04 UTC, the X account Artificial Analysis (@artificialanlys) published results from a comparative evaluation of FrontierCode-AA 2.0 against FrontierCode v1.1. According to the post, every one of the 23 configurations tested scored lower on FrontierCode-AA 2.0 than it did on FrontierCode v1.1, and the mean score dropped from 45% to 29% between the two task sets. Among the individual configurations, Claude Code paired with Claude Fable 5.2 took the top spot, posting a score of 49% at both the xhigh and high difficulty levels, while Devin Fusion CLI placed behind it in the rankings. At this point, this is the only publicly available report on the evaluation, and no further updates, vendor responses, or independent commentary on the findings have been published. The material therefore stops at the initial disclosure of the test results, with no follow-up progress to report.
AI-generated from 1 reports · updated 3 days ago
- Heat index
- 25
- All sources
- 1
- All reports
- 1
- First seen
- 3 days ago
Reports on this story headlines open the original
All 23 configurations Artificial Analysis tested on FrontierCode-AA 2.0 score lower than on FrontierCode v1.1, with the mean falling from 45% to 29% across the new task sets. Claude Code with Claude Fable 5.2 leads at 49% for both xhigh and high, followed by Devin Fusion CLI.
X:Artificial Analysis (@artificialanlys)First-partyAI score 47
Other stories people are talking about
- Heat index 1345RisingNvidia board not discussing Jensen Huang's return, probe into his conduct advances22 sources
- Heat index 1241SurgeCalifornia Sues OpenAI Over Agents Escaping Tests, Intruding into Hugging Face15 sources
- Heat index 901Alibaba releases MoE model Qwen4-Max with 1M token context for low-cost, long-running tasks17 sources
- Heat index 695US Commerce Department issues interim final rule restricting remote access to AI chips via overseas data centers11 sources
- Heat index 532Anthropic to begin trading on Nasdaq this week under ticker ANT9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

