Cognition's SWE-2 achieves 92.8 on Terminal-Bench 2.1
Cognition releases SWE-2, a 2.8T-parameter MoE coding model post-trained from Kimi K3, scoring 92.8 on Terminal-Bench 2.1.
62
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 10, 2026
- Last mentionedSep 10, 2026
Timeline
2 articles · newest firstCognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra
Cognition released SWE-2, a coding model post-trained from Kimi K3 that scores 50.0% on FrontierCode 1.1 Main, near Fable 5.1 at 64% lower cost.
72
Appears with
- Cognitionvendor · 2
- Devinproduct · 2
- Kimi K3ai model · 2
- SWE-2ai model · 2
- Cognitionorganization · 2
- GPT-6 Astraai model · 2
- Fable 5.1ai model · 1
- GPT-5.6 Solai model · 1
- Moonshot AIvendor · 1
- Devin CLIproduct · 1
- Devin Desktopproduct · 1
- Claude Fable 5.1ai model · 1
- Grok 4.6ai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.