Best of & Stacks

Research & News

…

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:

News Desk

Editorial Intelligence & Release Desk

AI Model News

50 dispatches published

Deep benchmark briefings, price reductions, and architecture analysis. Every dispatch links verified snapshot data and head-to-head showdowns.

All Launches Prices Versus Analysis

GPT-5 (2025) remains the legacy OpenAI flagship baseline

Aug 8, 2025·CompareLLM Intelligence Desk

GPT-5 (2025) remains the legacy OpenAI flagship baseline

Still a common compare target. 5.6 Sol replaced it as the buy; GPT-5 stays for old URLs.

gpt-5gpt-5-6-sol

PrevPage 5 of 5Next

1…45

Grok 4 remains the previous xAI flagship on this catalog

launch

Jul 10, 2025·CompareLLM Intelligence Desk

Grok 4 remains the previous xAI flagship on this catalog

2025-07 row. 4.6 is the buy. We keep 4 so upgrade pairs and old inbound links resolve.

grok-4grok-4-6

Read briefing

Gemini 2.5 Flash: previous Google speed workhorse, still a baseline

Mar 25, 2025·CompareLLM Intelligence Desk

Gemini 2.5 Flash: previous Google speed workhorse, still a baseline

Useful as a cheap historical compare. 3.7 Flash is the 2026 volume SKU.

gemini-2-5-flashgemini-3-7-flash

Gemini 2.5 Pro remains the previous Google long-context flagship

Mar 25, 2025·CompareLLM Intelligence Desk

Gemini 2.5 Pro remains the previous Google long-context flagship

2025-03 row. 3.x Pro replaced it. Kept for old “2.5 pro vs gpt-4o” inbound.

Command A: Cohere’s enterprise RAG and tool-use row

Mar 13, 2025·CompareLLM Intelligence Desk

Command A: Cohere’s enterprise RAG and tool-use row

Mar 2025. RAG and tools, not a frontier Elo play. Listed so “command a benchmark” has a sourced page.

Claude 3.7 Sonnet stays as a historical hybrid-reasoning baseline

Feb 25, 2025·CompareLLM Intelligence Desk

Claude 3.7 Sonnet stays as a historical hybrid-reasoning baseline

2025 hybrid-reasoning Sonnet. Deprecated for buying, kept for old compare URLs and “what did 3.7 score?”

claude-3-7-sonnet

DeepSeek R1 stays as the open-weights RL baseline

Jan 20, 2025·CompareLLM Intelligence Desk

DeepSeek R1 stays as the open-weights RL baseline

Jan 2025 reasoning model. Still searched. V4 Pro is the newer DeepSeek buy.

deepseek-r1deepseek-v4-pro

Codestral 25.01: Mistral’s code-specialist row

Jan 14, 2025·CompareLLM Intelligence Desk

Codestral 25.01: Mistral’s code-specialist row

Jan 2025 code model. Still a valid cheap-coding compare. Not a chatbot.

Llama 3.3 70B stays as the previous Meta 70B workhorse

Dec 6, 2024·CompareLLM Intelligence Desk

Llama 3.3 70B stays as the previous Meta 70B workhorse

Dec 2024 instruct 70B. Still a self-host baseline. Llama 4 is the 2026 buy.

llama-3-3-70bllama-4-maverick

GPT-4o stays as the 2024 compare anchor people still search

May 13, 2024·CompareLLM Intelligence Desk

GPT-4o stays as the 2024 compare anchor people still search

Deprecated for buying. Kept because “4o vs sonnet” is still a typed query.