FrontierCode v1.1 (Extended)

Extended task set of Cognition's FrontierCode with the same correctness + mergeability grading.

% solvedHigher is betterCounts toward:Weights: Coding ×0.7The test's websiteOfficial page ↗

The best 8 · 8 models tested

Top 8 · best setting per model · 8 models, 10 results (0 independent)

Measured by independent testersIndependent Reported by the makerVendor-reported

FrontierCode v1.1 (Extended) leaderboard
				Thinking levelSetting
1	Claude Opus 5.5	Anthropic	65.3%	Mediumadaptive thinking, effort=medium (best)	Maker's own figureVendor-reportedAnthropic ↗	Claude Code	22 Sep 2026
2	GPT-6 Astra	OpenAI	64.5%	Defaultbest score across efforts (OpenAI table: "maximum at any effort")	Maker's own figureVendor-reportedOpenAI ↗	—	3 Sep 2026
3	Claude Sonnet 5.5	Anthropic	64.4%	Extra highadaptive thinking, effort=xhigh	Maker's own figureVendor-reportedAnthropic ↗	Claude Code	28 Sep 2026
4	Claude Opus 5	Anthropic	63.6%	Mediumadaptive thinking, effort=medium (best)	Maker's own figureVendor-reportedAnthropic ↗	Claude Code	24 Jul 2026
5	Claude Fable 5.1	Anthropic	63.6%	Mediumadaptive thinking, effort=medium (best)	Maker's own figureVendor-reportedAnthropic ↗	Claude Code	1 Sep 2026
6	Grok 4.6	SpaceXAI (formerly xAI)	61.3%	High	Maker's own figureVendor-reportedSpaceXAI ↗	—	12 Aug 2026
7	GPT-5.6 Sol	OpenAI	60.6%	Defaultbest score across efforts (OpenAI table: "maximum at any effort")	Maker's own figureVendor-reportedOpenAI ↗	—	3 Sep 2026
8	Grok 4.5	SpaceXAI (formerly xAI)	56.6%	High	Maker's own figureVendor-reportedSpaceXAI ↗	—	12 Aug 2026