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
1367 models808 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

agents benchmark

DeepSWE 1.1 Leaderboard

DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

Updated Oct 23, 2026

Models51
Model coverage51
MetricScore
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

DeepSWE 1.1 Ranking

Higher score ranks better on this benchmark.

30 of 51 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelMEMuse Wonder FullMetaScore79.00%Percentile100.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank02ModelMEMuse Wonder FullMetaScore79.00%Percentile98.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank03ModelMEMuse WonderMetaScore78.80%Percentile96.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank04ModelMEMuse WonderMetaScore78.80%Percentile94.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank05ModelGOGemini 4 ArgonGoogleScore77.90%Percentile92.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank06ModelDEDeepSeek-V4.1-Flash-1017DeepSeekScore77.00%Percentile90.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank07ModelMEMuse Spark 1.3MetaScore75.40%Percentile88.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank08ModelOPGPT-6.1 SolOpenAIScore75.22%Percentile86.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank09ModelFAEmber-1Fireworks AIScore75.20%Percentile84.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank10ModelDEDeepSeek-V4.1-FlashDeepSeekScore74.20%Percentile82.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank11ModelANClaude Opus 5.5AnthropicScore74.20%Percentile80.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank12ModelOPGPT-6 AstraOpenAIScore74.10%Percentile78.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank13ModelGOGemini 3.8 FlashGoogleScore73.70%Percentile76.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank14ModelMIMiniMax M3.1 FlashMiniMaxScore73.70%Percentile74.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank15ModelOPGPT-5.6 SolOpenAIScore73.00%Percentile72.00%Participants51EvidenceBEvaluatedOct 22, 2026
Rank16ModelXIMiMo-V2.6-ProXiaomiScore71.90%Percentile70.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank17ModelXAGrok 4.7xAIScore71.00%Percentile68.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank18ModelANClaude Sonnet 5.5AnthropicScore71.00%Percentile66.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank19ModelANClaude Fable 5AnthropicScore70.00%Percentile64.00%Participants51EvidenceBEvaluatedOct 22, 2026
Rank20ModelOPGPT-5.6 TerraOpenAIScore70.00%Percentile62.00%Participants51EvidenceBEvaluatedOct 22, 2026
Rank21ModelMAKimi K3Moonshot AIScore69.00%Percentile60.00%Participants51EvidenceBEvaluatedOct 22, 2026
Rank22ModelANClaude Opus 5AnthropicScore68.80%Percentile58.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank23ModelOPGPT-6 SolOpenAIScore68.80%Percentile56.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank24ModelXIMiMo-V2.6-FlashXiaomiScore67.90%Percentile54.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank25ModelOPGPT-5.5OpenAIScore67.00%Percentile52.00%Participants51EvidenceBEvaluatedOct 22, 2026
Rank26ModelOPGPT-5.6 LunaOpenAIScore67.00%Percentile50.00%Participants51EvidenceBEvaluatedOct 22, 2026
Rank27ModelZAGLM-5.3Zhipu AIScore66.90%Percentile48.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank28ModelOPGPT-6 LunaOpenAIScore66.60%Percentile46.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank29ModelXAGrok 4.6xAIScore65.90%Percentile44.00%Participants51EvidenceCEvaluatedOct 22, 2026
Rank30ModelGOGemini 3.7 FlashGoogleScore65.30%Percentile42.00%Participants51EvidenceCEvaluatedOct 22, 2026

DeepSWE 1.1 Highlights

The leading models and scores on this benchmark.

DeepSWE 1.1 Score Distribution

A closer view of the leading scores on this benchmark.

DeepSWE 1.1

The Top AI Models for DeepSWE 1.1

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

What is DeepSWE 1.1?

What DeepSWE 1.1 measures and how its scores work.

DeepSWE 1.1 is a benchmark for evaluating software engineering agents.

It evaluates software engineering agents.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
DeepSWE 1.1
Modality
text
Primary category
agents
Score direction
higher
LLMBoard eligible
No
Evaluation key
overall

LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about DeepSWE 1.1.

Which model scores highest on DeepSWE 1.1?

Muse Wonder Full is currently ranked first with 79.00%.

What are the top three models on DeepSWE 1.1?

The current leaders are Muse Wonder Full (79.00%), Muse Wonder Full (79.00%), and Muse Wonder (78.80%).

Which DeepSWE 1.1 model has the lowest official input price?

GPT-6 Luna has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.

Which models are fastest among DeepSWE 1.1 results?

The fastest matched records are Gemini 3.7 Flash (409.96 tok/s via Google), GPT-5.6 Luna (215.52 tok/s via OpenAI), and Gemini 3.1 Pro (90.00 tok/s via Google).

Does the highest score result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does DeepSWE 1.1 measure?

It evaluates software engineering agents.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

51 model results are currently shown.

Does this benchmark affect the overall score?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1Muse Wonder Full79.00%
Rank #2Muse Wonder Full79.00%
Rank #3Muse Wonder78.80%
Rank #4Muse Wonder78.80%

Ranking basisThis deepswe 1.1 AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    ME
    Muse Wonder FullMeta
    Score
    79.00%

    Strengths

    • Ranks #1 of 51 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures DeepSWE 1.1, not total model capability
  2. 02
    ME
    Muse Wonder FullMeta
    Score
    79.00%

    Strengths

    • Ranks #2 of 51 compared models
    • 98th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures DeepSWE 1.1, not total model capability
  3. 03
    ME
    Meta
    Score
    78.80%
    Price
    $4.0 input / $20 output per 1M tokens

    Strengths

    • Ranks #3 of 51 compared models
    • 96th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures DeepSWE 1.1, not total model capability
  4. 04
    ME
    Meta
    Score
    78.80%
    Price
    $4.0 input / $20 output per 1M tokens

    Strengths

    • Ranks #4 of 51 compared models
    • 94th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures DeepSWE 1.1, not total model capability
  5. 05
    GO
    Google
    Score
    77.90%
    Price
    $2.0 input / $10 output per 1M tokens

    Strengths

    • Ranks #5 of 51 compared models
    • 92th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures DeepSWE 1.1, not total model capability

Selection summary

Best AI Models for DeepSWE 1.1

Muse Wonder Full currently leads DeepSWE 1.1 with 79.00%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Muse Wonder
Muse Wonder
Gemini 4 Argon
Benchmark rank #1Muse Wonder Full79.00%
Benchmark rank #2Muse Wonder Full79.00%
Benchmark rank #3Muse Wonder78.80% · $4.0 input / $20 output per 1M tokens