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

reasoning benchmark

Terminal-Bench 4.0 Leaderboard

Terminal-Bench 4.0 evaluates AI agents on 66 real-world tasks in terminal and command-line containerized environments, including science-adjacent and frontier engineering problems.

Updated Oct 23, 2026

Models29
Model coverage29
MetricScore
EvidenceB

On this page

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

Terminal-Bench 4.0 Ranking

Higher score ranks better on this benchmark.

29 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelANClaude Sonnet 5.5AnthropicScore70.60%Percentile100.00%Participants29EvidenceCEvaluatedOct 22, 2026
Rank02ModelANClaude Opus 5.5AnthropicScore66.40%Percentile96.43%Participants29EvidenceCEvaluatedOct 22, 2026
Rank03ModelANClaude Mythos 5.1AnthropicScore60.90%Percentile92.86%Participants29EvidenceCEvaluatedOct 22, 2026
Rank04ModelOPGPT-6 AstraOpenAIScore57.70%Percentile89.29%Participants29EvidenceCEvaluatedOct 22, 2026
Rank05ModelGOGemini 4 ArgonGoogleScore57.40%Percentile85.71%Participants29EvidenceCEvaluatedOct 22, 2026
Rank06ModelMEMuse Wonder FullMetaScore57.10%Percentile82.14%Participants29EvidenceCEvaluatedOct 22, 2026
Rank07ModelANClaude Fable 5.1AnthropicScore55.80%Percentile78.57%Participants29EvidenceCEvaluatedOct 22, 2026
Rank08ModelMEMuse WonderMetaScore52.00%Percentile75.00%Participants29EvidenceCEvaluatedOct 22, 2026
Rank09ModelANClaude Opus 5AnthropicScore51.80%Percentile71.43%Participants29EvidenceBEvaluatedOct 22, 2026
Rank10ModelANClaude Fable 5AnthropicScore44.50%Percentile67.86%Participants29EvidenceBEvaluatedOct 22, 2026
Rank11ModelDEDeepSeek-V4.1-Flash-1017DeepSeekScore42.30%Percentile64.29%Participants29EvidenceCEvaluatedOct 22, 2026
Rank12ModelZAGLM-5.3Zhipu AIScore41.80%Percentile60.71%Participants29EvidenceBEvaluatedOct 22, 2026
Rank13ModelINLing 3.1 FlashInclusionaiScore40.40%Percentile57.14%Participants29EvidenceCEvaluatedOct 12, 2026
Rank14ModelANClaude Haiku 5.5AnthropicScore39.20%Percentile53.57%Participants29EvidenceCEvaluatedOct 22, 2026
Rank15ModelMIMiniMax M3.1 FlashMiniMaxScore38.10%Percentile50.00%Participants29EvidenceCEvaluatedOct 22, 2026
Rank16ModelXAGrok 4.7xAIScore38.00%Percentile46.43%Participants29EvidenceCEvaluatedOct 22, 2026
Rank17ModelOPGPT-5.6 SolOpenAIScore37.30%Percentile42.86%Participants29EvidenceBEvaluatedOct 22, 2026
Rank18ModelXIMiMo-V2.6-ProXiaomiScore34.90%Percentile39.29%Participants29EvidenceCEvaluatedOct 22, 2026
Rank19ModelDEDeepSeek-V4.1-FlashDeepSeekScore31.20%Percentile35.71%Participants29EvidenceCEvaluatedOct 22, 2026
Rank20ModelXIMiMo-V2.6-FlashXiaomiScore28.80%Percentile32.14%Participants29EvidenceCEvaluatedOct 22, 2026
Rank21ModelMAMistral Large 4Mistral AIScore28.30%Percentile28.57%Participants29EvidenceCEvaluatedOct 22, 2026
Rank22ModelANClaude Opus 4.8AnthropicScore23.60%Percentile25.00%Participants29EvidenceBEvaluatedOct 22, 2026
Rank23ModelOPGPT-5.6 TerraOpenAIScore21.50%Percentile21.43%Participants29EvidenceBEvaluatedOct 22, 2026
Rank24ModelXAGrok 4.6xAIScore20.30%Percentile17.86%Participants29EvidenceBEvaluatedOct 22, 2026
Rank25ModelGOGemini 3.8 FlashGoogleScore19.10%Percentile14.29%Participants29EvidenceCEvaluatedOct 22, 2026
Rank26ModelOPGPT-5.6 LunaOpenAIScore17.30%Percentile10.71%Participants29EvidenceBEvaluatedOct 22, 2026
Rank27ModelANClaude Sonnet 5AnthropicScore12.40%Percentile7.14%Participants29EvidenceBEvaluatedOct 22, 2026
Rank28ModelXAGrok 4.5xAIScore12.40%Percentile3.57%Participants29EvidenceBEvaluatedOct 22, 2026
Rank29ModelUPSolar Mini 4UpstageScore1.00%Percentile0.00%Participants29EvidenceBEvaluatedOct 22, 2026

Terminal-Bench 4.0 Highlights

The leading models and scores on this benchmark.

Terminal-Bench 4.0 Score Distribution

A closer view of the leading scores on this benchmark.

Terminal-Bench 4.0

The Top AI Models for Terminal-Bench 4.0

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

What is Terminal-Bench 4.0?

What Terminal-Bench 4.0 measures and how its scores work.

Terminal-Bench 4.0 is a reasoning benchmark for AI agents working in terminal and command-line containerized environments.

It measures performance across 66 tasks using the Score metric, reported as a ratio.

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

Family
Terminal-Bench 4.0
Modality
text
Primary category
reasoning
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 Terminal-Bench 4.0.

Which model scores highest on Terminal-Bench 4.0?

Claude Sonnet 5.5 is currently ranked first with 70.60%.

What are the top three models on Terminal-Bench 4.0?

The current leaders are Claude Sonnet 5.5 (70.60%), Claude Opus 5.5 (66.40%), and Claude Mythos 5.1 (60.90%).

Which Terminal-Bench 4.0 model has the lowest official input price?

Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.

Which models are fastest among Terminal-Bench 4.0 results?

The fastest matched records are GPT-5.6 Luna (215.52 tok/s via OpenAI), Grok 4.5 (80.00 tok/s via xAI), and Gemini 3.8 Flash (55.66 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 Terminal-Bench 4.0 measure?

It measures performance across 66 tasks using the Score metric, reported as a ratio.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

29 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 #1Claude Sonnet 5.570.60%
Rank #2Claude Opus 5.566.40%
Rank #3Claude Mythos 5.160.90%
Rank #4GPT-6 Astra57.70%

Ranking basisThis terminal-bench 4.0 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
    AN
    Claude Sonnet 5.5Anthropic
    Score
    70.60%
    Price
    $2.0 input / $10 output per 1M tokens
    Speed
    Up to 42.00 tok/s via Anthropic

    Strengths

    • Ranks #1 of 29 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures Terminal-Bench 4.0, not total model capability
  2. 02
    AN
    Claude Opus 5.5Anthropic
    Score
    66.40%
    Price
    $4.0 input / $20 output per 1M tokens
    Speed
    Up to 12.33 tok/s via Anthropic

    Strengths

    • Ranks #2 of 29 compared models
    • 96th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures Terminal-Bench 4.0, not total model capability
  3. 03
    AN
    Anthropic
    Score
    60.90%

    Strengths

    • Ranks #3 of 29 compared models
    • 93th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures Terminal-Bench 4.0, not total model capability
  4. 04
    OP
    OpenAI
    Score
    57.70%
    Price
    $10 input / $50 output per 1M tokens

    Strengths

    • Ranks #4 of 29 compared models
    • 89th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures Terminal-Bench 4.0, not total model capability
  5. 05
    GO
    Google
    Score
    57.40%
    Price
    $2.0 input / $10 output per 1M tokens

    Strengths

    • Ranks #5 of 29 compared models
    • 86th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures Terminal-Bench 4.0, not total model capability

Selection summary

Best AI Models for Terminal-Bench 4.0

Claude Sonnet 5.5 currently leads Terminal-Bench 4.0 with 70.60%. 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.

Claude Mythos 5.1
GPT-6 Astra
Gemini 4 Argon
Benchmark rank #1Claude Sonnet 5.570.60% · $2.0 input / $10 output per 1M tokens
Benchmark rank #2Claude Opus 5.566.40% · $4.0 input / $20 output per 1M tokens
Benchmark rank #3Claude Mythos 5.160.90%