- FrontierCode 1.1 Main 50
- DeepSWE 1.1 73
- Terminal-Bench 2.1 92.8
- Terminal-Bench 4.0 27.3
SWE-2
SWE-2 ranks first on Terminal-Bench 2.1.
Cognition Released 10 Sep 2026
6
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Cognition Sep 2026
SWE-2
Closed weights
No Epoch Capabilities Index score yet
- FrontierCode 2.0 23.8% #14 /26
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| FrontierCode | 50% | #8 of 46 | Epoch AI | |
| DeepSWE | 73% | #13 of 51 | Model card | |
| FrontierCode 2.0 | 23.8% | #14 of 26 | Official leaderboard | |
| FrontierCode 1.1 | 50% | #7 of 12 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Terminal-Bench 2.1 | 92.8% | #1 of 53 | Model card | |
| Terminal-Bench 4.0 | 27.3% | #21 of 23 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.