# SWE-2 Flash

> Cognition's small coding model, released November 4, 2026 — trained from Thinking Machines' Inkling-Small and sold at one-fifth the price of SWE-2.

- Maker: Cognition
- Line: SWE Flash
- Canonical page: https://ai-tldr.dev/models/swe-2-flash/
- Updated: 2026-11-04

## In short

SWE-2 Flash is a coding model from Cognition, the company behind Devin, released on 4 November 2026. You can use it through Devin (Cognition).

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Licence | Proprietary · API only | [1] |
| Released | 4 November 2026 | [2] |
| Parameters | 276B total / 12B active (inherited from Inkling-Small) | [1] |

## Sources

1. [Devin documentation](https://docs.devin.ai/)
2. [Introducing SWE-2 Flash (Cognition blog)](https://cognition.com/blog/swe-2-flash)

## Overview

SWE-2 Flash is a coding model from Cognition, the company behind Devin, released on 4 November 2026. It is the smaller sibling of SWE-2: Cognition describes it as one-fifth the price and three times the speed of SWE-2, and built it for the everyday share of agent work — automations, code review, feature development and documentation updates — that smaller models can increasingly handle. In the launch post's generation-speed replay, SWE-2 Flash runs at 200 tokens per second against 60 for SWE-2.

Where SWE-2 was post-trained from Moonshot AI's Kimi K3, SWE-2 Flash starts from Inkling-Small, the 276B-total, 12B-active open-weight model from Thinking Machines Lab, and Cognition calls it a fully American coding model. For the first time in its recipe, Cognition added a large mid-training stage before reinforcement learning: a few trillion tokens of scientific articles, blogs, code and other sources, fed in three stages so the scarcest, highest-quality data came last. The RL stage that followed used more diverse, more carefully audited tasks than SWE-2's. Cognition reports this lifted Terminal-Bench 4.0 from 0.9% for the base model to 20.0%, and FrontierCode 2.0 from 3.2% to 24.0% — slightly above SWE-2's 23.8% on that benchmark.

Cognition also trained for cybersecurity work, raising the model's ExploitBench score from 11.3% to 34.8%. Citing the risk that the same skills help attackers, it did not publish the weights; instead it said it is building a program to share them securely with trusted industry partners and research labs. At launch, SWE-2 Flash is reached through Devin Desktop and the Devin CLI.

## Benchmarks

- FrontierCode 2.0: 24% ([source](https://cognition.com/blog/swe-2-flash))
- FrontierCode 1.1 Main: 45.5% ([source](https://cognition.com/blog/swe-2-flash))
- Terminal-Bench 2.1: 89.2% ([source](https://cognition.com/blog/swe-2-flash))
- Terminal-Bench 4.0: 20% ([source](https://cognition.com/blog/swe-2-flash))
- DeepSWE 1.1: 60.1% ([source](https://cognition.com/blog/swe-2-flash))
- SWE-Bench Pro v2 Hard: 89.9% ([source](https://cognition.com/blog/swe-2-flash))
- ExploitBench: 34.8% ([source](https://cognition.com/blog/swe-2-flash))

## Strengths

- Large gains over its base model: Terminal-Bench 4.0 from 0.9% to 20.0% and FrontierCode 2.0 from 3.2% to 24.0%, per Cognition
- Matches its much larger sibling on FrontierCode 2.0 (24.0% vs 23.8% for SWE-2) at one-fifth the price
- Fast: 200 tokens per second in Cognition's replay, against 60 for SWE-2
- Ahead of Inkling-Small, Beam 1.0, Muse Spark Open, GLM 5.3 Flash and DeepSeek V4.1 Flash on both FrontierCode 2.0 and FrontierCode 1.1 Main in Cognition's table
- Trained for defensive security work: 34.8% on ExploitBench, up from 11.3% for the base model

## Best for

- High-volume Devin work where cost and latency matter more than peak capability — automations, code review, documentation updates
- Feature development tasks routed to a cheaper model, keeping SWE-2 for the hardest long-horizon jobs
- Interactive work in Devin Desktop and the Devin CLI, where 200 tokens per second shortens the wait
- Security-focused engineering, given the model's ExploitBench training

## How to access

- [Devin (Cognition)](https://docs.devin.ai/)

## SWE Flash versions

- SWE-2 Flash (4 November 2026): First SWE Flash model: mid-trained and RL-tuned on Inkling-Small; 24.0% on FrontierCode 2.0 at one-fifth SWE-2's price. — this page

## FAQ

### Is SWE-2 Flash open source?

No. Its base model, Inkling-Small, is open-weight, but Cognition did not publish SWE-2 Flash's weights, citing cyber risk. It said it is building a program to share them securely with trusted industry partners and research labs.

### What model is SWE-2 Flash built on?

Inkling-Small from Thinking Machines Lab, a Mixture-of-Experts model with 276B total and 12B active parameters. Cognition added a mid-training stage of a few trillion tokens, then reinforcement learning, on top of it.

### How does SWE-2 Flash differ from SWE-2?

SWE-2 is post-trained from the 2.8T-parameter Kimi K3; SWE-2 Flash from the much smaller Inkling-Small. Cognition puts SWE-2 Flash at one-fifth the price and 3x the speed. It edges SWE-2 on FrontierCode 2.0 (24.0% vs 23.8%) but trails it on FrontierCode 1.1 Main (45.5% vs 50.0%), DeepSWE 1.1 (60.1% vs 73.0%) and Terminal-Bench 4.0 (20.0% vs 27.3%).

### Where can I use SWE-2 Flash?

In Devin Desktop and the Devin CLI, from launch day. Cognition offered it free through November 30, 2026. The launch post does not mention a standalone API.

### What is SWE-2 Flash's context window?

Cognition does not state one in the launch post, so we do not list a figure.

## Links

- [Introducing SWE-2 Flash (Cognition blog)](https://cognition.com/blog/swe-2-flash)
- [Introducing SWE-2 (Cognition blog)](https://cognition.com/blog/swe-2)
- [FrontierCode benchmark](https://cognition.com/frontiercode)
- [Devin documentation](https://docs.devin.ai/)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/swe-2-flash/