Mindber
HomeDiscoverRankingsModel ArenaWhat's NewComparePricingBlog
Mindber

Independent directory for discovering, comparing, and monitoring AI apps, agents, and automation software by category, pricing, traffic, regional demand, alternatives, and verified activity signals.

All systems operational
ENEnglishCN中文ESEspañolIDIndonesiaVITiếng ViệtTHไทย

Product

  • AI software directory
  • AI software rankings
  • Compare AI apps
  • AI software pricing
  • Submit an AI product

Resources

  • AI scoring methodology
  • AI activity signals
  • AI rankings methodology
  • Verification tiers
  • Methodology changelog
  • AI data sources
  • AI product blog
  • AI market reports

Company

  • About Mindber
  • Claim a profile
  • Report correction
  • Contact Mindber

Legal

  • Terms
  • Privacy
  • Disclaimer
  • DMCA
  • Takedown

Mindber publishes human-reviewed AI product profiles, rankings, comparisons, and reports from publicly accessible product, pricing, traffic, regional, and source data, with clear context for buyers, search engines, and AI answer engines. Not investment, legal, or purchasing advice.

Mindber Score™, Mindber Innovation Index™, Mindber Functionality Score™, and Mindber Activity Score™ are trademarks of Mindber.

© 2026 Mindber. All rights reserved.v2.5
  • Home
  • Discover
  • Rankings
  • Model Arena
  • Compare
  • Sign in
Skip to main content
Rankings/Methodology

Mindber Model Index — Methodology

How we rank AI models across quality, speed, and price into one number.

Data sources

Arena.ai — Crowd ELO

Real user pairwise comparisons across 12 boards: Agent, Text, Search, Vision, Document, Code (WebDev + Image-to-WebDev). Each model's position on each board contributes a vote-weighted quality signal.

Artificial Analysis — Objective benchmarks

Provider-agnostic measurements of Intelligence Index, output speed (t/s), latency (TTFT), and blended price per 1M tokens — updated continuously across 200+ model–provider combinations.

What we exclude

Image and video generation boards (text-to-image, image-edit, text-to-video, image-to-video, video-edit) are excluded from the MMI. These boards rank creative generation models on aesthetic preference — a different task class from language reasoning. Mixing them with text LLMs produces a misleading composite.

Formula

Step 1 — Percentile normalization

Every raw metric is converted to a percentile rank within its own pool so different scales are comparable. Speed and price use lower-is-better inversion (faster = higher percentile; cheaper = higher percentile). Result: all signals live in [0, 1].

Step 2 — Quality fusion (Q)

Arena and AA each produce a quality estimate. Confidence in each source is weighted before fusing:

cA = totalVotes / (totalVotes + 2000) // Arena confidence; saturates at ≈1 for high-vote models

cAA = 1 if model appears in AA data, else 0

Q = (cA × qArena + cAA × qAA) / (cA + cAA)

qArena is the vote-weighted mean of the model's per-board Arena percentiles. qAA is its AA Intelligence Index percentile. Models with no quality signal from either source are excluded.

Step 3 — Composite score (raw)

Efficiency metrics (speed, latency, price) are blended with Q using the Overall preset weights. Missing metrics are dropped and remaining weights are renormalized, so a model with no price data isn't penalized.

raw = (W_q×Q + W_s×spd + W_l×lat + W_p×prc) / (W_q + present_weights)

Step 4 — Coverage shrinkage

Models with thin data (few votes, only one source) are shrunk toward the median to prevent a handful of votes from catapulting an obscure model to the top.

presence = (hasArena ? 1 : 0 + hasAA ? 1 : 0) / 2

coverage = presence × (0.5 + 0.5 × cA) // clamped [0, 1]

MMI = 100 × (raw × coverage + median_raw × (1 − coverage))

A model with millions of votes and AA data has coverage ≈ 1 and its MMI equals its raw score × 100. A model with 50 votes and no AA data gets pulled toward the pack median.

Rank by presets

The Rank by toggle on the Overall board re-weights and re-ranks client-side without a new data fetch. Sub-scores (quality, speed, latency, price) are shipped with each row for this purpose.

PresetQuality (Q)SpeedLatencyPriceUse case
Overall60%12%8%20%Default — balanced across all signals
Frontier90%3%3%4%Quality-dominant; cost & speed ignored
Value45%10%5%40%Intelligence per dollar
Speed45%25%20%10%Latency-sensitive applications

Weights are renormalized over present metrics per model — missing efficiency data does not count against a model.

Attribution

  • Arena.ai — crowd preference data, Agent Arena methodology, pairwise comparison infrastructure
  • Artificial Analysis — objective intelligence benchmarks, speed, latency, and pricing data

Mindber does not claim ownership of source data. MMI is a derived, compute-on-read composite computed from publicly available leaderboard snapshots. Last methodology revision: 2026-06-14.

Questions about this methodology? Contact support@mindber.com.← Back to Leaderboard

On this page

  • Data sources
  • What we exclude
  • Formula
  • Rank by presets
  • Attribution

Related

  • Model Arena
  • Rankings
Sign In
Skip to main content
Rankings/Methodology

Mindber Model Index — Methodology

How we rank AI models across quality, speed, and price into one number.

Data sources

Arena.ai — Crowd ELO

Real user pairwise comparisons across 12 boards: Agent, Text, Search, Vision, Document, Code (WebDev + Image-to-WebDev). Each model's position on each board contributes a vote-weighted quality signal.

Artificial Analysis — Objective benchmarks

Provider-agnostic measurements of Intelligence Index, output speed (t/s), latency (TTFT), and blended price per 1M tokens — updated continuously across 200+ model–provider combinations.

What we exclude

Image and video generation boards (text-to-image, image-edit, text-to-video, image-to-video, video-edit) are excluded from the MMI. These boards rank creative generation models on aesthetic preference — a different task class from language reasoning. Mixing them with text LLMs produces a misleading composite.

Formula

Step 1 — Percentile normalization

Every raw metric is converted to a percentile rank within its own pool so different scales are comparable. Speed and price use lower-is-better inversion (faster = higher percentile; cheaper = higher percentile). Result: all signals live in [0, 1].

Step 2 — Quality fusion (Q)

Arena and AA each produce a quality estimate. Confidence in each source is weighted before fusing:

cA = totalVotes / (totalVotes + 2000) // Arena confidence; saturates at ≈1 for high-vote models

cAA = 1 if model appears in AA data, else 0

Q = (cA × qArena + cAA × qAA) / (cA + cAA)

qArena is the vote-weighted mean of the model's per-board Arena percentiles. qAA is its AA Intelligence Index percentile. Models with no quality signal from either source are excluded.

Step 3 — Composite score (raw)

Efficiency metrics (speed, latency, price) are blended with Q using the Overall preset weights. Missing metrics are dropped and remaining weights are renormalized, so a model with no price data isn't penalized.

raw = (W_q×Q + W_s×spd + W_l×lat + W_p×prc) / (W_q + present_weights)

Step 4 — Coverage shrinkage

Models with thin data (few votes, only one source) are shrunk toward the median to prevent a handful of votes from catapulting an obscure model to the top.

presence = (hasArena ? 1 : 0 + hasAA ? 1 : 0) / 2

coverage = presence × (0.5 + 0.5 × cA) // clamped [0, 1]

MMI = 100 × (raw × coverage + median_raw × (1 − coverage))

A model with millions of votes and AA data has coverage ≈ 1 and its MMI equals its raw score × 100. A model with 50 votes and no AA data gets pulled toward the pack median.

Rank by presets

The Rank by toggle on the Overall board re-weights and re-ranks client-side without a new data fetch. Sub-scores (quality, speed, latency, price) are shipped with each row for this purpose.

PresetQuality (Q)SpeedLatencyPriceUse case
Overall60%12%8%20%Default — balanced across all signals
Frontier90%3%3%4%Quality-dominant; cost & speed ignored
Value45%10%5%40%Intelligence per dollar
Speed45%25%20%10%Latency-sensitive applications

Weights are renormalized over present metrics per model — missing efficiency data does not count against a model.

Attribution

  • Arena.ai — crowd preference data, Agent Arena methodology, pairwise comparison infrastructure
  • Artificial Analysis — objective intelligence benchmarks, speed, latency, and pricing data

Mindber does not claim ownership of source data. MMI is a derived, compute-on-read composite computed from publicly available leaderboard snapshots. Last methodology revision: 2026-06-14.

Questions about this methodology? Contact support@mindber.com.← Back to Leaderboard

On this page

  • Data sources
  • What we exclude
  • Formula
  • Rank by presets
  • Attribution

Related

  • Model Arena
  • Rankings