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
1281 models767 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

LiveBench reasoning (2026-06-25) Leaderboard

All tasks required; arithmetic mean: theory_of_mind, zebra_puzzle, spatial, logic_with_navigation

Updated Sep 25, 2026

Models41
Model coverage41
Metricreasoning
EvidenceB

On this page

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

LiveBench reasoning (2026-06-25) Ranking

Higher reasoning ranks better on this benchmark.

30 of 41 rows
Columns

Show columns

Sort by
Rank
Model
reasoning
Percentile
Participants
Evidence
Evaluated
Rank01ModelOPGPT-6 AstraOpenAIreasoning92.65 scorePercentile100.00%Participants41EvidenceBEvaluatedN/A
Rank02ModelOPGPT-5.6 SolOpenAIreasoning91.65 scorePercentile97.50%Participants41EvidenceBEvaluatedN/A
Rank03ModelMAKimi K3Moonshot AIreasoning90.67 scorePercentile95.00%Participants41EvidenceBEvaluatedN/A
Rank04ModelOPGPT-5.6 TerraOpenAIreasoning90.63 scorePercentile92.50%Participants41EvidenceBEvaluatedN/A
Rank05ModelXAGrok 4.6xAIreasoning90.51 scorePercentile90.00%Participants41EvidenceBEvaluatedN/A
Rank06ModelMEMuse Spark 1.2Metareasoning90.00 scorePercentile87.50%Participants41EvidenceBEvaluatedN/A
Rank07ModelOPGPT-5.5OpenAIreasoning89.65 scorePercentile85.00%Participants41EvidenceBEvaluatedN/A
Rank08ModelMEMuse Spark 1.3Metareasoning89.65 scorePercentile82.50%Participants41EvidenceBEvaluatedN/A
Rank09ModelGOGemini 3.8 FlashGooglereasoning89.29 scorePercentile80.00%Participants41EvidenceBEvaluatedN/A
Rank10ModelACQwen3.8 MaxAlibaba Cloud / Qwen Teamreasoning88.21 scorePercentile77.50%Participants41EvidenceBEvaluatedN/A
Rank11ModelOPGPT-5.4OpenAIreasoning88.12 scorePercentile75.00%Participants41EvidenceBEvaluatedN/A
Rank12ModelGOGemini 3.7 FlashGooglereasoning87.80 scorePercentile72.50%Participants41EvidenceBEvaluatedN/A
Rank13ModelMEMuse Spark 1.1Metareasoning87.73 scorePercentile70.00%Participants41EvidenceBEvaluatedN/A
Rank14ModelACQwen3.8-Flash-NextAlibaba Cloud / Qwen Teamreasoning87.38 scorePercentile67.50%Participants41EvidenceBEvaluatedN/A
Rank15ModelXAGrok 4.5xAIreasoning87.17 scorePercentile65.00%Participants41EvidenceBEvaluatedN/A
Rank16ModelDEDeepSeek-V4-Flash-0731DeepSeekreasoning86.63 scorePercentile62.50%Participants41EvidenceBEvaluatedN/A
Rank17ModelDEDeepSeek-V4-Pro-0813DeepSeekreasoning85.84 scorePercentile60.00%Participants41EvidenceBEvaluatedN/A
Rank18ModelZAGLM-5.3Zhipu AIreasoning85.80 scorePercentile57.50%Participants41EvidenceBEvaluatedN/A
Rank19ModelOPGPT-5.6 LunaOpenAIreasoning85.64 scorePercentile55.00%Participants41EvidenceBEvaluatedN/A
Rank20ModelDEDeepSeek-V4-Flash-Vision-ExpDeepSeekreasoning85.40 scorePercentile52.50%Participants41EvidenceBEvaluatedN/A
Rank21ModelGOGemini 3.6 FlashGooglereasoning85.15 scorePercentile50.00%Participants41EvidenceBEvaluatedN/A
Rank22ModelGOGemini 3.1 ProGooglereasoning84.00 scorePercentile47.50%Participants41EvidenceBEvaluatedN/A
Rank23ModelACQwen3.7 MaxAlibaba Cloud / Qwen Teamreasoning83.34 scorePercentile45.00%Participants41EvidenceBEvaluatedN/A
Rank24ModelOPGPT-5.2OpenAIreasoning83.21 scorePercentile42.50%Participants41EvidenceBEvaluatedN/A
Rank25ModelMAKimi K2.7 CodeMoonshot AIreasoning82.81 scorePercentile40.00%Participants41EvidenceBEvaluatedN/A
Rank26ModelXAGrok 4.7xAIreasoning82.65 scorePercentile37.50%Participants41EvidenceBEvaluatedN/A
Rank27ModelGOGemini 3.5 FlashGooglereasoning82.00 scorePercentile35.00%Participants41EvidenceBEvaluatedN/A
Rank28ModelOPGPT-5.4 nanoOpenAIreasoning81.10 scorePercentile32.50%Participants41EvidenceBEvaluatedN/A
Rank29ModelACQwen3.8-27BAlibaba Cloud / Qwen Teamreasoning80.03 scorePercentile30.00%Participants41EvidenceBEvaluatedN/A
Rank30ModelMAKimi K2.6Moonshot AIreasoning79.38 scorePercentile27.50%Participants41EvidenceBEvaluatedN/A

LiveBench reasoning (2026-06-25) Highlights

The leading models and scores on this benchmark.

LiveBench reasoning (2026-06-25) Score Distribution

A closer view of the leading scores on this benchmark.

LiveBench reasoning (2026-06-25)

The Top AI Models for LiveBench reasoning (2026-06-25)

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

What is LiveBench reasoning (2026-06-25)?

What LiveBench reasoning (2026-06-25) measures and how its scores work.

All tasks required; arithmetic mean: theory_of_mind, zebra_puzzle, spatial, logic_with_navigation

Scores are shown in score. This benchmark is verified and has an evidence level of B.

Family
livebench-reasoning
Modality
text
Primary category
reasoning
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
overall

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

FAQ

Common questions about LiveBench reasoning (2026-06-25).

Which model scores highest on LiveBench reasoning (2026-06-25)?

GPT-6 Astra is currently ranked first with 92.65 score.

What are the top three models on LiveBench reasoning (2026-06-25)?

The current leaders are GPT-6 Astra (92.65 score), GPT-5.6 Sol (91.65 score), and Kimi K3 (90.67 score).

Which LiveBench reasoning (2026-06-25) model has the lowest official input price?

DeepSeek-V4-Flash-0731 has the lowest matched official input price at $0.15 input / $0.60 output per 1M tokens.

Which models are fastest among LiveBench reasoning (2026-06-25) results?

The fastest matched records are Gemini 3.6 Flash (188.24 tok/s via Google), Gemini 3.5 Flash-Lite (185.11 tok/s via Google), and Gemini 3.8 Flash (155.60 tok/s via Google).

Does the highest reasoning 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 LiveBench reasoning (2026-06-25) measure?

All tasks required; arithmetic mean: theory_of_mind, zebra_puzzle, spatial, logic_with_navigation

Is a higher reasoning better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

41 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.

Rank #1GPT-6 Astra92.65 score
Rank #2GPT-5.6 Sol91.65 score
Rank #3Kimi K390.67 score
Rank #4GPT-5.6 Terra90.63 score

Ranking basisThis livebench reasoning (2026-06-25) AI model leaderboard uses descending reasoning in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    OP
    GPT-6 AstraOpenAI
    reasoning
    92.65 score
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 25.98 tok/s via OpenAI

    Strengths

    • Ranks #1 of 41 compared models
    • 100th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench reasoning (2026-06-25), not total model capability
  2. 02
    OP
    GPT-5.6 SolOpenAI
    reasoning
    91.65 score
    Price
    $4.0 input / $20 output per 1M tokens
    Speed
    Up to 35.30 tok/s via OpenAI

    Strengths

    • Ranks #2 of 41 compared models
    • 98th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench reasoning (2026-06-25), not total model capability
  3. 03
    MA
    Moonshot AI
    reasoning
    90.67 score
    Price
    $3.0 input / $15 output per 1M tokens
    Speed
    Up to 4.03 tok/s via Moonshot AI

    Strengths

    • Ranks #3 of 41 compared models
    • 95th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench reasoning (2026-06-25), not total model capability
  4. 04
    OP
    OpenAI
    reasoning
    90.63 score
    Price
    $2.0 input / $12 output per 1M tokens
    Speed
    Up to 51.62 tok/s via OpenAI

    Strengths

    • Ranks #4 of 41 compared models
    • 93th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench reasoning (2026-06-25), not total model capability
  5. 05
    XA
    xAI
    reasoning
    90.51 score
    Price
    $2.0 input / $6.0 output per 1M tokens
    Speed
    Up to 34.92 tok/s via xAI

    Strengths

    • Ranks #5 of 41 compared models
    • 90th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench reasoning (2026-06-25), not total model capability

Selection summary

Best AI Models for LiveBench reasoning (2026-06-25)

GPT-6 Astra currently leads LiveBench reasoning (2026-06-25) with 92.65 score. 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.

Kimi K3
GPT-5.6 Terra
Grok 4.6
Benchmark rank #1GPT-6 Astra92.65 score · $10 input / $50 output per 1M tokens
Benchmark rank #2GPT-5.6 Sol91.65 score · $4.0 input / $20 output per 1M tokens
Benchmark rank #3Kimi K390.67 score · $3.0 input / $15 output per 1M tokens