Skip to content
ModelRankAI
  • Models
  • Rankings
  • Benchmarks
  • Compare
  • Methodology
  • Reviews
  • About

ModelRankAI

Evidence-driven AI model evaluation.

Models

  • Models
  • Compare

Rankings

  • Rankings
  • Benchmarks

About

  • Methodology
  • About
  • Reviews

© 2026 Artificial Intelligence DataBase. All rights reserved.

Admin
Models / Llama Open

Llama Open

Sample data

By Meta AI

Open-weight model included to demonstrate coverage of open models.

  • Status: active
  • Context: 128,000 tokens
  • Modalities: text, code
  • Released: 2025-10-01
Add to comparisonBrowse rankings
Performance snapshot

How this model ranks

Official rankings are evidence-weighted and profile-specific. Community opinion is shown separately below.

9.7top available profile

Ranking positions

See where the model lands under each ranking profile.

General AI Reasoning#4
9.7

66% confidence · 567 evidence

Partial evidence
Coding#4
8.0

72% confidence · 446 evidence

Reasoning#4
7.0

85% confidence · 220 evidence

Value / Quality#4
30.5

76% confidence · 421 evidence

Multi-dimensional performance

Cost Efficiency71
71% evidence confidence1 evidence
Reasoning0
94% evidence confidence40 evidence
Knowledge0
100% evidence confidence90 evidence
Instruction Following0
100% evidence confidence60 evidence
Coding0
100% evidence confidence120 evidence
Writing0
88% evidence confidence30 evidence
Tool Use0
85% evidence confidence25 evidence
Speed0
100% evidence confidence200 evidence
Context0
71% evidence confidence1 evidence

About

Sample profile with fewer benchmark entries to demonstrate low-evidence handling.

Evidence

Benchmark results

Results below come from different benchmarks with different tasks and metrics — they are not directly comparable to each other, only across models within the same benchmark.

Benchmark results for this model
BenchmarkScoreSample sizeConfidenceEvidenceEvaluated
General Reasoning Eval71 %4035%L2Benchmark Result2026-07-01

Community reviews

★★★★★3.4(1 review)

Based on a small number of reviews — shown as a conservative estimate rather than the raw average (3.0) until more reviews come in.

  • 5 star0
  • 4 star0
  • 3 star1
  • 2 star0
  • 1 star0

Community ratings are a separate signal from expert evaluations and benchmark evidence — see the model’s Evidence section above for those.

All usesCodingWritingResearchCustomer supportImage generationGeneral useOther
  • ★★★★★General use

    Good value for the price

    Sample review: not as strong on complex reasoning tasks but the cost makes it viable for high-volume, lower-stakes use cases.

    2026-07-10 Sample data

Write a review

Rating