BenchSift
FR

AI Models

1543

Latest models

  1. Simba 3.5SpeechifyAI
  2. JT-4.1 Flash 236B A21BChina Mobile
  3. H3-Image HighspeedMiniMax

At a glance

Claude Fable 5.2 (Default Fallback) leads with 64.6 (Intelligence Index), out of 568 ranked models. Best score for the money: Agnes 3.0 Flash, 35.5 for $0.075 per million tokens. Fastest: Mercury 2.5, 522 t/s.

Value and speed are picked among the top 284, so a cheap or quick run with a low score never wins. Data retrieved on Nov 12, 2026.

Rank by

32 results of 568

  1. 9
    Muse Wonder Full (Max)MetaNot public. Artificial Analysis measured this model but marks it as not publicly available (checkered pattern in its charts). Its rank still follows its measurements.Reasoning
    50.1
  2. 17
    Muse WonderMeta · $8 · 113 t/sReasoning
    43.6
  3. 25
    Muse Spark 1.2 (Xhigh)Meta · $2 · 204 t/sReasoning
    39.6
  4. 31
    Muse Spark 1.3Meta · $2 · 138 t/sReasoning
    36.6
  5. 33
    Muse EmberMeta · 448 t/sNewReasoningFormer stealth model
    36.0
  6. 44
    Muse Spark 1.1 (Xhigh)Meta · $2 · 187 t/sReasoning
    33.7
  7. 55
    Muse SparkMetaReasoning
    31.3
  8. 104
    Muse Spark Open (Xhigh)Meta · $2 · 157 t/sNewReasoningOpen weights
    24.9
  9. 291
    Llama 4 MaverickMeta · $0.417 · 71.4 t/sOpen weights
    9.3
  10. 350
    Llama 3.3 Instruct 70BMeta · $0.627 · 73 t/sOpen weights
    7.7
  11. 353
    Meta: Llama 3.3 70B InstructMeta · $0.71Open weights
    7.7
  12. 377
    Llama 3.1 Instruct 405BMetaOpen weights
    7.3
  13. 402
    Llama 3.1 Instruct 8BMeta · $0.043 · 121 t/sOpen weights
    6.9
  14. 404
    Meta: Llama 3.1 8B InstructMeta · $0.025Open weights
    6.9
  15. 419
    Llama 3.1 Instruct 70BMeta · $0.56 · 14.2 t/sOpen weights
    6.6
  16. 425
    Meta: Llama 3.1 70B InstructMeta · $0.72Open weights
    6.6
  17. 429
    Llama 4 ScoutMeta · $0.30 · 89 t/sOpen weights
    6.5
  18. 434
    Llama 3.2 Instruct 90B (Vision)MetaOpen weights
    6.4
  19. 440
    Muse Glimmer (High)Meta · $0.525 · 88.4 t/sReasoningOpen weights
    6.3
  20. 444
    Muse Glimmer 30BMeta · $0.525ReasoningOpen weights
    6.3

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy