Skip to main content
BenchLM

FrontierCode 1.1 Extended

We show this table for reference; we do not rank on it.

Data verified 34 confirmed releases in the last 30 daysFollow model changes

Cognition's 150-task Extended subset of the FrontierCode 1.1 software-engineering benchmark.

Benchmark score on FrontierCode 1.1 Extended — September 27, 2026

We compile the FrontierCode 1.1 Extended rows from provider self-reports. GPT-6 Astra leads the table at 64.5%, followed by Claude Opus 5 (63.6%) and Claude Opus 5.5 (63.6%). We do not use these results to rank models overall.

1Proprietary

GPT-6 Astra

OpenAI

64.5%
Overall 88.69Context 1.05M
2Proprietary

Claude Opus 5

Anthropic

63.6%
Overall 79.81
3Proprietary

Claude Opus 5.5

Anthropic

63.6%
Overall 86.98Context 1M

7 modelsCodingCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (7 models)

Score
1
GPT-6 AstraOpenAI · Closed
64.5%
2
Claude Opus 5Anthropic · Closed
63.6%
3
Claude Opus 5.5Anthropic · Closed
63.6%
4
Grok 4.6xAI · Closed
61.3%
5
GPT-5.6 SolOpenAI · Closed
60.6%
6
GPT-5.6 TerraOpenAI · Closed
55.8%
7
GPT-5.6 LunaOpenAI · Closed
55.1%

Among the reported FrontierCode 1.1 Extended rows, GPT-6 Astra is first at 64.5%. The third row is 0.9 points behind. The broader top-10 range is 9.4 points, so many of the published results sit in a relatively narrow band.

7 models have been evaluated on FrontierCode 1.1 Extended. The benchmark falls in the Coding category. FrontierCode 1.1 Extended is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About FrontierCode 1.1 Extended

Year

2026

Tasks

150 private software-engineering tasks

Format

Repository task completion with maintainer rubrics

Difficulty

Frontier coding-agent quality

BenchLM stores Cognition's published GPT-5.6 scores on FrontierCode 1.1 Extended as display-only evidence. The tasks are private and the results combine a model with the Devin harness, so they are excluded from weighted rankings.

GPT-5.6 models are now available in Devin

Freshness and provenance

Version

FrontierCode 1.1 Extended

Refresh cadence

Static

Staleness state

Current

Question availability

Private tasks with public aggregate results

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does FrontierCode 1.1 Extended measure?

Cognition's 150-task Extended subset of the FrontierCode 1.1 software-engineering benchmark.

Which model scores highest on FrontierCode 1.1 Extended?

GPT-6 Astra by OpenAI currently leads with a score of 64.5% on FrontierCode 1.1 Extended.

How many models are evaluated on FrontierCode 1.1 Extended?

7 AI models have been evaluated on FrontierCode 1.1 Extended on BenchLM.

Compare top models on FrontierCode 1.1 Extended

GPT-6 Astra vs Claude Opus 5Claude Opus 5 vs Claude Opus 5.5Claude Opus 5.5 vs Grok 4.6Grok 4.6 vs GPT-5.6 Sol
Last updated: September 27, 2026 · BenchLM version FrontierCode 1.1 Extended

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.