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

5 results of 568

  1. 74
    Step 5 PreviewStepFun · $1.43 · 149 t/sReasoningOpen weights
    28.5
  2. 153
    Step 3.7 FlashStepFun · $0.438 · 144 t/sReasoningOpen weights
    19.5
  3. 167
    Step 3.5 Flash 2603StepFun · $0.15 · 102 t/sReasoningOpen weights
    17.0
  4. 169
    Step 3.5 FlashStepFun · $0.15 · 125 t/sReasoningOpen weights
    17.0
  5. 351
    Step3 VL 10BStepFunReasoningOpen weights
    7.7

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