Cognition model product
8-trillion-parameter Kimi K3 using reinforcement learning.
Updated Nov 22, 2026. Default version: SWE-2
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for SWE-2.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkTerminal-Bench 2.1 | Score92.80% | Rank01 | Participants58 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 1.1 | Score50.00% | Rank07 | Participants25 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score73.00% | Rank18 | Participants59 | Percentile70.69% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score27.30% | Rank30 | Participants41 | Percentile27.50% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for SWE-2. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionSWE-2 | Released | LLMBoard75.63 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about SWE 2 and its available data.
SWE 2 is a coding model from Cognition. Starting 2026-09-10, it is available in Devin Desktop and Devin CLI, with rollout to Devin Web and Fusion in progress.
Data as of 2026-11-21.
Common questions about SWE 2.
SWE 2's default version was released on Sep 10, 2026.
No official standard PAYG price is currently available for SWE 2.
SWE 2 was created by Cognition.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.