# Cognition Releases SWE-2 Flash Coding Model in Devin Desktop and CLI, With Weights Not Yet Public

Published 2026-11-06 · AI.info Team · AI.info

> Cognition’s SWE-2 Flash is available in Devin Desktop and CLI, with faster generation and a lower price than SWE-2. The company reports gains on several coding benchmarks and is developing a program to share the model’s weights with trusted partners and researchers.

SWE-2 Flash is, [Cognition](https://cognition.com/blog/swe-2-flash) says, a fully American coding model that sets a new bar for intelligence at low cost and high speed. It is available today in Devin Desktop and CLI, at one-fifth the price and three times the speed of SWE-2, the company says. Cognition is not sharing the weights publicly yet. The company is building a program to share them securely with trusted industry partners and research labs, with more information expected in a few weeks.

## Reported Gains Over Inkling-Small

SWE-2 Flash improves Terminal-Bench 4.0 from 0.9% to 20.0% and FrontierCode 2.0 from 3.2% to 24.0% compared with its base model, Inkling-Small, according to Cognition. On DeepSWE 1.1, the announcement lists scores of 60.1 for SWE-2 Flash and 17.4 for Inkling-Small. The new model outperforms all American open-weight models on leading evaluations, including models three times larger, the company says.

The results table also compares the two models on other tasks. SWE-2 Flash scores 45.5 on FrontierCode 1.1 Main, compared with 21.5 for Inkling-Small, and 89.2 on Terminal-Bench 2.1, compared with 64.7. On SWE-Atlas QA, their listed scores are 50.0 and 27.4; on SWE-Bench Pro v2 Hard, they are 89.9 and 56.5. SWE-2 Flash’s ExploitBench score is 34.8, up from 11.3 for Inkling-Small, Cognition reports.

## Generation Listed at 200 Tokens Per Second

Cognition lists SWE-2 Flash’s generation speed at 200 tokens per second, compared with 60 tokens per second for SWE-2. Its demonstration replays each model’s run on Terminal-Bench 4.0’s gsea-proteomics task at simulated speeds of 200 and 60 tokens per second. The transcripts are shortened to equal length for the comparison. SWE-2 Flash is also free through 11/30, according to the announcement.

## Training combined mid-training and reinforcement learning

Cognition added a mid-training stage before reinforcement learning, starting from Inkling-Small, which has 276 billion total parameters and 12 billion active parameters. To guide decisions about training data, the company curated a held-out coding dataset intended to reflect model intelligence in real-world software engineering scenarios. It compared candidate data mixes by measuring how many tokens each required to reach the same validation loss as a baseline mix.

The company settled on a mid-training dataset made up of a few trillion tokens of high-quality scientific articles, blogs, code and other sources. Training took place in three stages, with the scarcest, highest-quality data used later. Cognition then carried out large-scale reinforcement learning. Most of the improvements came from higher quality and greater diversity in its reinforcement-learning tasks, the company says. The company audited task instructions, environment setup and verifiers, and curated new task types to cover a wider range of capabilities.

## Cognition cites cyber risks in its weights decision

Enterprises and governments need observability and the ability to host and control deployments on their own infrastructure, including on-premises, Cognition says. Researchers also need to study model behavior and potential misuse, the company says. One goal for SWE-2 Flash is to give industry partners and researchers transparent access to weights, along with the ability to fine-tune and run the model in sensitive environments.

Cognition targeted cybersecurity work during training to help defenders, raising SWE-2 Flash’s ExploitBench score from 11.3% to 34.8%, the company says. Cognition also warns that the same capabilities could be used by malicious attackers, pointing to a recent surge in cyber attacks. That risk is why the weights are not being shared publicly yet, the company says, while it develops a secure-sharing program for trusted industry partners and research labs.

## Sources

1. Original source · Blog post [Cognition](https://cognition.com/blog/swe-2-flash) cognition.com

## Companies in this story

- [Cognition AI](https://ai.info/companies/cognition-ai)

## Related stories

- [OpenAI’s GPT-6 Astra Scores 87.4% Across 20 Coding Languages](https://ai.info/news/openai-gpt-6-astra-multilangbench-low-resource-coding)
- [Cognition Crosses $1B in Annualized Revenue Run Rate, Company Says](https://ai.info/news/cognition-annualized-revenue-run-rate-1-billion)
- [Hugging Face Upload Billed as a 14T Anthropic Checkpoint Was Seeded Noise](https://ai.info/news/anthropic-14t-mythos-checkpoint-hugging-face-fake)
- [Thinking Machines Lab Plans Apache 2.0 Weights for Inkling 2 Small, a 594B-Parameter Model](https://ai.info/news/thinking-machines-inkling-2-small)
- [Baidu Releases ERNIE 5.5 Flash Base Weights](https://ai.info/news/baidu-ernie-5-5-flash-base-weights)

## Explore

[More articles](https://ai.info/news)

---

Canonical: https://ai.info/news/cognition-swe-2-flash-restricts-weight-access
