Skip to model comparison
AI Agent Store/Model comparisonsBuild an AI worker ↗

AI AGENT STORE · MODEL MOMENTUM INDEX

Most popular models
with Hermes.

Find your next agent model. Compare popularity and recent trends, see the relative cost, and launch with your choice already selected.

14 scored modelsUpdated 2026-11-13Trend through 2026-11-12 · UTC

Our 0–100 index combines popularity with a recent-trend adjustment of up to 20% in either direction. It reflects the observed sample; it is not a quality benchmark or a count of users. Score differences are index points, not “times more popular.”

FIRST IN THIS RANKING

DeepSeek V4.1 Flash 1017

67.45 / 100 · Reference cost: 1×

Launch with Hermes ↗
Economy · below 0.95×Standard · 0.95–3×Premium · 3× or more

The momentum ranking

  1. 01

    DeepSeek V4.1 Flash 1017

    67.45 / 100
    Standard · Default · 1×
  2. 02

    DeepSeek V4.1 Flash (September)

    67.32 / 100
    Standard · About 0.57–1.1× the cost
  3. 03

    Upstage: Solar Mini 4

    49.59 / 100
    Economy · About 0.17–0.33× the cost
  4. 04

    Z.ai: GLM 5.3 Flash

    44.60 / 100
    Economy · About 0.099–0.2× the cost
  5. 05

    MiniMax M3.1 Flash

    39.94 / 100
    Standard · About 0.25–1× the cost
  6. 06

    Step 5 Preview

    32.18 / 100
    Premium · About 2.8–5.6× the cost
  7. 07

    NVIDIA: Nemotron 3 Ultra

    27.26 / 100
    Premium · About 2–4× the cost
  8. 08

    Anthropic: Claude Opus 5.5

    26.91 / 100
    Premium · About 15–30× the cost
  9. 09

    Z.ai: GLM 5.3

    22.09 / 100
    Premium · About 1.6–3.3× the cost
  10. 10

    StepFun: Step 3.7 Flash

    20.08 / 100
    Standard · About 0.81–1.6× the cost
  11. 11

    Anthropic: Claude Sonnet 5.5

    18.18 / 100
    Premium · About 7.5–15× the cost
  12. 12

    Xiaomi: MiMo-V2.6-Pro

    15.62 / 100
    Standard · About 1.1–2.2× the cost
  13. 13

    Gemini 4 Argon

    13.60 / 100
    Premium · About 7.5–15× the cost
  14. 14

    MiniMax: MiniMax M3

    13.41 / 100
    Standard · About 1–2× the cost

How we calculate the index

MMI = popularity score × (1 + recent-trend adjustment), capped at 100. Popularity is the foundation. Recent growth or decline can adjust it by at most 20%.

Popularity uses the source’s published monthly aggregate. For the trend, the latest three complete UTC days receive 50%, 30% and 20% weight, newest first. We compare that weighted share with the preceding three days using the same weights. The current partial day is excluded from the trend.

Every supported model with a verified monthly popularity observation qualifies, even with limited daily history. If any of the six trend days is missing, its adjustment is neutral and the model stays listed. We include all currently supported models with a published popularity observation.

This ranking uses popularity and trend observations for this harness only. Exact model versions are scored separately. The launch selector also includes all other supported available models.

Formula details

Let s be the model’s share of the published monthly aggregate. Popularity P = 100 × ln(1 + 100s) / ln(101). Let r be the weighted daily share for the latest three complete days and b the same weighted share for the preceding three days. Adjustment a = clamp(r/b − 1, −0.20, +0.20). If b is zero and r is positive, a = +0.20; if both are zero or the six-day trend is incomplete, a = 0. The harness index is min(100, P × (1 + a)), rounded to two decimals. Combined scores average the available harness indices. Equal scores sort by model name.

Prices and choosing a model

Cost comparisons use Platform Credit rates with an illustrative mix of 80% input and 20% output tokens. The first model in this page is the reference. The combined page’s reference can differ from the recommendation for an individual harness. Long-context and time-based price changes can produce a range; the highest known multiplier determines the price category. An unquantified premium rate also requires confirmation.

A higher index does not promise better results, and a higher price does not guarantee a smarter model. Test the tasks that matter to you. Running agents keep their chosen model.

Sources and updates

AI Agent Store calculates this index from public Hermes observations and OpenClaw observations published by OpenRouter. They cover activity visible to that source, excluding direct-provider and local use. The source groups some models into “Others”; we do not treat missing individual figures as zero.

The daily catalog review validates model availability and pricing, then runs the same calculation and publishes the updated snapshot. If validation fails, the previous verified snapshot is retained. Monthly popularity observed: 2026-11-13. Last calculation: .

AI Agent Store · Model comparisons · Data reviewed 2026-11-13Sources, limitations & corrections ↗