# SWE-1.7 Benchmark Scores & Performance

> SWE-1.7 by Cognition has 4 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/swe-1-7

Last updated: October 6, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Cognition |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: SWE
- Variant: base
- Benchmarks covered: 4 of 613
- Sibling models: [SWE-2](/models/swe-2)
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 81.5% | [Cognition: SWE-1.7 launch post](https://cognition.com/blog/swe-1-7) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [FrontierCode 1.1 Main](/benchmarks/frontiercode) | 42.3% | [Cognition: SWE-1.7 launch post](https://cognition.com/blog/swe-1-7) |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 81.5% | [Cognition: SWE-1.7 launch post](https://cognition.com/blog/swe-1-7) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 77.8% | [Cognition: SWE-1.7 launch post](https://cognition.com/blog/swe-1-7) |

## Other Cognition Models

- [SWE-2](/models/swe-2) - Score: not computed