SWE-2

SWE-2 is a reasoning model from Cognition in the SWE family. 3 benchmarks count toward its score, in 2 categories.

partialShows if the model has enough results for an index.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.40%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
77.8
CodingCode writing and repair.
78.0
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
N/A
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
N/A

Results

3 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Terminal-Bench 2.1 (provider run)Agentic92.8%78.8DeepSeek-AI
Terminal-Bench 2.1 (provider run)Agentic92.8%78.8DeepSeek-AI
DeepSWEAgentic73.0%76.8Datacurve AI
FrontierCode 1.1 MainCoding50.0%78.0Cognition

3 benchmarks count, from 4 of 4 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authors

More from Cognition

SWE-1.7Unranked