llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1464 models816 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Cognition model product

SWE 2

8-trillion-parameter Kimi K3 using reinforcement learning.

Updated Nov 22, 2026. Default version: SWE-2

LLMBoard Score75.6SWE-2
Coverage20%4 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

SWE 2 Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

SWE-2 LLMBoard score breakdown

SWE 2 Benchmark Results

Benchmark scores for SWE-2.

4 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkTerminal-Bench 2.1Score92.80%Rank01Participants58Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkFrontierCode 1.1Score50.00%Rank07Participants25Percentile75.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkDeepSWE 1.1Score73.00%Rank18Participants59Percentile70.69%EvidenceCEvaluatedNov 21, 2026
BenchmarkTerminal-Bench 4.0Score27.30%Rank30Participants41Percentile27.50%EvidenceCEvaluatedNov 21, 2026

SWE 2 Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

SWE 2 Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

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.

SWE 2 Runtime Performance

Provider-specific output speed and catalog latency for SWE-2. Runtime does not affect the capability score.

No runtime data

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.

SWE 2 Specifications

Technical details for the model's default version.

Version
SWE-2
Released
Sep 10, 2026
Knowledge cutoff
Unknown
Parameters
N/A
Context window
N/A
Max output
N/A
Inputs
text
Outputs
text
Open weights
No
License
Proprietary

SWE 2 Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionSWE-2ReleasedSep 10, 2026LLMBoard75.63ParametersN/AContextN/AMax outputN/AOpen weightsNoLicenseProprietary

Models similar to SWE 2

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#71-5.71
CO

SWE 2 Flash

Cognition

69.92 LLMBoard

Details
#45-0.03
GO

Gemini 3.7 Flash

Google

75.60 LLMBoard

Details
#46-0.06
AN

Claude Opus 4.6

Anthropic

75.57 LLMBoard

Details
#47-0.11
MI

MiniMax M3.1 Flash

MiniMax

75.52 LLMBoard

Details
#48-0.24
AN

Claude Sonnet 5

Anthropic

75.39 LLMBoard

Details
#49-0.58
AN

Claude Haiku 5.5

Anthropic

75.05 LLMBoard

Details

What is SWE 2?

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.

FAQ

Common questions about SWE 2.

When was SWE 2 released?

SWE 2's default version was released on Sep 10, 2026.

How much does SWE 2 cost?

No official standard PAYG price is currently available for SWE 2.

Who created SWE 2?

SWE 2 was created by Cognition.

What is the context window for SWE 2?

A context window is not available for the default version.

Is SWE 2 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer SWE 2?

No provider offering is currently linked to the default version.

Browse runtime rankings