Find the right AI for you

Search by name or tell us what you want to do
API servicesChoose how to access modelsAI modelsCapabilities, specifications, and pricingAI toolsFind useful tools by taskMCP directoryConnect tools, data, and workflowsAgent skillsFind reusable skills for AI agentsBenchmarksCompare model performanceOnline toolsConvert accounts, format JSON, estimate costs and test APIsModel timelineExplore model releasesUse casesStart with a practical task
EnterSearch · ↑↓Choose a resultEscClose
Submit中文
MODEL CAPABILITY · PRICE & RELEASES

Capabilities

Artificial Analysis · Compare benchmark results, text costs and release dates separately, with each model and configuration identified.

Data as of2026-10-28 · 273 configurations

Methodology & original report ↗

Capability comparison

One capability index · top configuration per developer · excludes estimates, retired models and future releases.

Chart data · 10 entries
NameCapability index
Gemini 4 Carbon59.426
Claude Opus 5.558.406
GPT-6 Astra56.854
Muse Wonder Full49.727
Kimi K3.1 Pro46.003
Grok 4.735.012
Qwen3.8 Max (0902)33.555
DeepSeek V4.1 Flash 101732.49
GLM-5.331.653
MiMo-V2.6-Pro29.89

Capability and text cost

Index ≥30 · cost = (3 × input price + output price) ÷ 4, in USD per million tokens. Showing 42 of 42 configurations, selected by capability.

Chart data · 42 entries
NameCost / capability
Gemini 4 Carbon (High)8 / 59.426
Claude Opus 5.5 (Max, Default Fallback)8 / 58.406
Claude Opus 5.5 (Xhigh, Default Fallback)8 / 56.995
GPT-6 Astra (Max)20 / 56.854
GPT-6 Astra (Xhigh)20 / 55.256
GPT-6 Astra (High)20 / 54.85
GPT-6.1 Sol (Max)4 / 54.509
Claude Sonnet 5.5 (Max, Default Fallback)4 / 54.241
GPT-6.1 Sol (Xhigh)4 / 52.308
Claude Opus 5.5 (High, Default Fallback)8 / 51.686
GPT-6 Astra (Medium)20 / 51.455
GPT-6.1 Terra (Max)2 / 50.977
Gemini 4 Argon (High)8 / 50.412
GPT-6.1 Sol (High)4 / 50.229
Claude Fable 5.1 (Xhigh, Default Fallback)20 / 49.672
Claude Sonnet 5.5 (Xhigh, Default Fallback)4 / 49.574
Claude Fable 5.1 (Max, Default Fallback)20 / 49.01
Claude Opus 5.5 (Medium, Default Fallback)8 / 48.058
Claude Fable 5.1 (High, Default Fallback)20 / 47.025
GPT-6.1 Sol (Medium)4 / 46.147
Kimi K3.1 Pro4 / 46.003
GPT-6.1 Terra (Xhigh)2 / 44.95
Muse Wonder (Max)8 / 43.325
GPT-6 Astra (Low)20 / 43.035
Claude Fable 5.1 (Medium, Default Fallback)20 / 42.972
GPT-6.1 Terra (High)2 / 42.334
Claude Sonnet 5.5 (High, Default Fallback)4 / 41.115
Claude Fable 5.1 (Low, Default Fallback)20 / 38.484
GPT-6.1 Terra (Medium)2 / 38.115
Claude Haiku 5.5 (Max)0.2 / 36.235
Grok 4.7 (High)3 / 35.012
GPT-6.1 Sol (Low)4 / 34.503
Claude Opus 5.5 (Low, Default Fallback)8 / 34.503
Claude Haiku 5.5 (Xhigh)0.2 / 34.339
Grok 4.7 (Xhigh)3 / 34.335
Qwen3.8 Max (0902)3 / 33.555
DeepSeek V4.1 Flash 1017 (Max)0.525 / 32.49
GLM-5.3 (Max)2.15 / 31.653
Grok 4.7 (Low)3 / 30.882
Gemini 3.8 Flash (High)1.5 / 30.547
GPT-6.1 Terra (Non-reasoning)2 / 30.416
Claude Sonnet 5.5 (Medium, Default Fallback)4 / 30.32

CapabilitiesDetails

Sorted by capability index, with reasoning configurations kept separate. Estimates and historical records follow rank-eligible entries.

On this page20records
  1. —

    LFM2 24B A2B

    Liquid AI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  2. —

    LFM2.5-1.2B-Instruct

    Liquid AI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  3. —

    LFM2.5-1.2B-Thinking

    Liquid AI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  4. —

    LFM2.5-2.6B

    Liquid AI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  5. —

    LFM2.5-8B-A1B

    Liquid AI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  6. —

    LFM2.5-VL-1.6B

    Liquid AI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  7. —

    Ling-3.0-flash-Fin

    InclusionAI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  8. —

    Ling-3.0-flash-VL

    InclusionAI

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  9. —

    Ling 3.0 Tiny

    InclusionAI

    Capability index
    —
    Input / million tokens
    $0
    Output / million tokens
    $0
    Value · 3:1 usage mix
    —
  10. —

    Ling 3.1 Flash

    InclusionAI

    Capability index
    —
    Input / million tokens
    $0.3
    Output / million tokens
    $0.9
    Value · 3:1 usage mix
    —
  11. —

    Llama 3.1 Instruct 405B

    Meta

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  12. —

    Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

    NVIDIA

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  13. —

    Llama 3.2 Instruct 11B (Vision)

    Meta

    Capability index
    —
    Input / million tokens
    $0.345
    Output / million tokens
    $0.345
    Value · 3:1 usage mix
    —
  14. —

    Llama 3.2 Instruct 90B (Vision)

    Meta

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  15. —

    Llama 3.3 Instruct 70B

    Meta

    Capability index
    —
    Input / million tokens
    $0.6
    Output / million tokens
    $0.71
    Value · 3:1 usage mix
    —
  16. —

    Llama 4 Maverick

    Meta

    Capability index
    —
    Input / million tokens
    $0.25
    Output / million tokens
    $0.92
    Value · 3:1 usage mix
    —
  17. —

    Llama 4 Scout

    Meta

    Capability index
    —
    Input / million tokens
    $0.18
    Output / million tokens
    $0.66
    Value · 3:1 usage mix
    —
  18. —

    LongCat 2.0

    LongCat

    Capability index
    —
    Input / million tokens
    $0.75
    Output / million tokens
    $2.95
    Value · 3:1 usage mix
    —
  19. —

    LongCat Flash Lite

    LongCat

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
  20. —

    Magistral Medium 1.2

    Mistral

    Capability index
    —
    Input / million tokens
    —
    Output / million tokens
    —
    Value · 3:1 usage mix
    —
Ranking criteria & test conditions
  • Intelligence scores come from the same leaderboard snapshot. Reasoning configurations remain separate; estimated scores and retired models are excluded from the highlights.
  • Release dates follow the report and are separate from our update dates. Undated models are excluded from recent releases. A report’s date is not treated as independent proof of an official model release.
  • Text prices use USD per million tokens, with input and output stored separately. Subscription, cache and media charges are not mixed into this comparison.
  • Value picks require an intelligence score of at least 30 and rank by score ÷ (3 × input price + output price) × 4, selecting the highest value for each developer. This assumes a 3:1 text input/output ratio; actual task costs vary.
  • Developer highlights show one representative per developer. Model aliases and reasoning configurations are not automatically mapped to a specific catalog version. Full results retain the original configurations and missing values.
  • This snapshot uses Artificial Analysis Intelligence Index v5.0. Different index versions are not directly comparable.

Charts are calculated from the full report, independently of the detail page. Release activity uses release dates, not changes in model capability over time. Missing prices are not zero costs.