AI Model Scoreboard
AI Model Scoreboard
Evidence-first scoring for AI models.
SCORESMETHODOLOGY
AI Model Scoreboard
© 2026 · Evidence-first · Open metrics · Community supported
SupportDonateChangelogHealth: Checking

Data is aggregated from public sources; please verify before making critical decisions.

AI Model Scoreboard is informational only and does not provide investment, compliance, or security advice.

← Back to v4

MODEL: EleutherAI: Llemma 7b

Provider: eleutheraiSource: MissingmodelKey: eleutherai/llemma-7b
Overall
69.7 / 100

A) Absolute Metrics (must exist for all models)

Model key
eleutherai/llemma-7b
Display name
Missing
status: missing
  • missing_field:displayName
Provider
Missing
status: missing
  • missing_field:provider
Canonical slug
Missing
status: missing
  • missing_field:canonicalSlug
Context length
Missing
status: missing
  • missing_field:contextLength
Max output tokens
Missing
status: missing
  • missing_field:maxOutputTokens
Pricing input per 1M
Missing
status: missing
  • missing_field:pricingInputPer1M
Pricing output per 1M
Missing
status: missing
  • missing_field:pricingOutputPer1M
Modalities
Missing
status: missing
  • missing_field:modalities
Supports tools
Missing
status: missing
  • missing_field:supportsTools
Supports JSON
Missing
status: missing
  • missing_field:supportsJson
Release date
Missing
status: missing
  • missing_field:releaseDate
Training cutoff
Missing
status: missing
  • missing_field:trainingCutoff

Adoption & Decision

Missing

Reasons:

  • missing_decision_entry — Evidence indicates missing/failed; penalty applied per policy.
References: None

Status

full

Reasons (from decisions.json):

No published decision record.

Score Summary

Overall: 70 / 100

Overall = Σ(weight × score)

Category Totals

CategoryWeightScoreContrib
C1 Performance0.4000.00
C2 Spec0.2000.00
C3 Cost0.1200.00
C4 Speed0.1000.00
C5 Reliability0.0800.00
C6 Features0.0600.00
C7 Transparency0.0400.00

Category Scores (0–100)

  • performance76
  • safety50
  • adoption71
  • openness58
  • cost100

Top drivers

No score driver details were available.

C) Evidence (4 tiles/cards; reasons required if not ok)

Evidence Quality: 0/100

Based on evidence availability only. Does not affect the score.

Show quality breakdown
  • official_page not_found +0.00
  • dev_activity not_found +0.00
  • paper not_found +0.00
  • audit not_found +0.00

Official page

type: official_page

⚠️ not_found

No reliable source was found.

url: No link provided.

SPEC VIOLATION: Spec missing evidence: evidence URLs are required for this score.

reasons (1)

codes:

  • missing:type:official_page
How this affected scoring

not_found => openness and transparency scores reduced / penalty applied.

extracted
No extracted data.

Dev activity

type: dev_activity

⚠️ not_found

No reliable source was found.

url: No link provided.

SPEC VIOLATION: Spec missing evidence: evidence URLs are required for this score.

reasons (1)

codes:

  • missing:type:dev_activity
How this affected scoring

not_found => dev-activity score capped / penalty applied.

extracted
No extracted data.

Paper

type: paper

⚠️ not_found

No reliable source was found.

url: No link provided.

SPEC VIOLATION: Spec missing evidence: evidence URLs are required for this score.

reasons (1)

codes:

  • missing:type:paper
How this affected scoring

not_found => transparency score reduced / penalty applied.

extracted
No extracted data.

Audit

type: audit

⚠️ not_found

No reliable source was found.

url: No link provided.

SPEC VIOLATION: Spec missing evidence: evidence URLs are required for this score.

reasons (1)

codes:

  • missing:type:audit
How this affected scoring

not_found => audit and safety scores reduced / penalty applied.

extracted
No extracted data.

Detail data unavailable

HTTP status: 404

Model not found: eleutherai/llemma-7b

Links

No links recorded.