CompareLLM.ai
Live
Leaderboard
Models
Compare
Best of & Stacks
Research & News
…
CompareLLM.ai
Precision Benchmarks

Programmatic, dated AI model benchmarks, head-to-head comparisons, and Stack Engine presets.

Daily ingest · 06:00 UTC

Analytics & Benchmarks

  • AI Model Leaderboard
  • Head-to-Head Compare Hub
  • Models Directory
  • Stack Engine Presets
  • Frontier Models
  • Open Weights Catalog

Guides & Intent Lists

  • Best LLM Lists (2026)
  • Best Coding LLM
  • Best Cheap LLM
  • Fastest Low-Latency LLM
  • Claude vs GPT Benchmark
  • What is Elo?
  • Methodology Guides
  • News & Dispatches

Transparency & API

  • Evaluation Methodology
  • Benchmark Changelog
  • Public JSON API
  • llms.txt Specification
  • Privacy Policy
  • Sign In / Account

© 2026 CompareLLM. Public benchmark data aggregated from Arena Elo, LiveBench, SWE-bench & OpenRouter.

Every score has a dated snapshot.

Theme:
Currency:
  1. Home
  2. Changelog
Automated Audit Trail
RSS Feed

Benchmark Changelog

Logged automatically by daily ingest workers when any score shifts beyond sensitivity thresholds or when new models are promoted.

Aug 16, 2026

Permalink →
Catalog refresh: Claude Opus 5 / Fable 5 / Sonnet 5, GPT-5.6 Sol·Terra·Luna, Gemini 3.6/3.7 Flash, Grok 4.6 Aug 12 prices, GLM-5.3 and Qwen3.8 27B (Aug 14).
Organic/GEO layer: What is Elo guide, answer-first boxes, FAQ schema, AI crawlers allowed, admin ingest/alias/promote desk. DeepSeek V4-Pro-0813 alias added. No official flagship after Aug 14.
Catalog add: Claude Haiku 4.5 ($1/$5 official) and Llama 4 Scout (open-weight long-context) for cheap-alternative compares.
Same-class predecessors: Claude 3 Opus / Opus 4 / 3.5 Sonnet / Sonnet 4 / 3.5 Haiku, GPT-4 Turbo, Grok 3, DeepSeek V3, Llama 3.1 70B, Gemini 1.5 Pro.

Aug 14, 2026

Permalink →
qwen-3-8-27bAlibaba published Qwen3.8 27B open weights.
glm-5-3Z.ai launched GLM-5.3 (post-train of GLM-5.2). Weights delayed for a safety review.

Aug 13, 2026

Permalink →
gemini-3-7-flashGoogle shipped Gemini 3.7 Flash at $0.75/$3.75 intro pricing.

Aug 12, 2026

Permalink →
grok-4-6xAI Grok 4.6 post-training refresh. Seed Elo/price snapshots updated.