CompareLLM
CompareLLM.ai
Live
LeaderboardModelsCompareStacksBest ofGuidesNewsMethod
…
CompareLLM
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.

  1. Home
  2. Providers
  3. Anthropic
AI Provider Portfolio
31 active models in catalog

Anthropic Models

Comprehensive benchmark scores, coding performance, latency metrics, and API pricing for all models developed by Anthropic.

Flagship ModelClaude Opus 5
Portfolio Avg Elo1468 Elo
Browse Other Providers
OpenAIGooglexAI

Available Models & Verified Benchmarks

#1Claude Opus 5
Proprietary

Anthropic current default flagship. Official API $5/$25 per 1M tokens and a 1M context window (Anthropic, Jul 24 2026).

Elo1,624
SWE-bench79.2%
Out $/1M$50
Model Fact Sheetvs all hub
#2Claude Fable 5
Proprietary

Anthropic top-tier long-horizon model. Official API $10/$50 per 1M tokens (Claude Platform pricing, Aug 2026).

Elo1,616
SWE-bench80%
Out $/1M$50
Model Fact Sheetvs all hub
#3Claude Opus 4.8
Proprietary

Prior Opus generation still billed at $5/$25. Kept as a compare baseline against Opus 5.

Elo1,598
SWE-bench78.4%
Out $/1M$25
Model Fact Sheetvs all hub
#4Claude Opus 4.6
Proprietary

Follow-on Opus release. Slightly behind 4.5 on official SWE-bench bash-only in the last published sweep; stronger long-horizon agent traces.

Elo1,574
SWE-bench75.9%
Out $/1M$25
Model Fact Sheetvs all hub
#5Claude Opus 4.5
Proprietary

Anthropic frontier coding and computer-use model. SWE-bench leader on the official mini-SWE-agent harness in the Feb 2026 refresh.

Elo1,568
SWE-bench76.8%
Out $/1M$25
Model Fact Sheetvs all hub
#6Claude Sonnet 5
Proprietary

Anthropic workhorse. Official $2/$10 per 1M tokens made permanent on Aug 10 2026.

Elo1,556
SWE-bench73.8%
Out $/1M$10
Model Fact Sheetvs all hub
#7Claude Sonnet 4.5
Proprietary

Workhorse Anthropic model: most of Opus coding quality at a mid-tier price.

Elo1,524
SWE-bench70.1%
Out $/1M$15
Model Fact Sheetvs all hub
#8Claude Opus 4
Proprietary

First Claude 4 Opus generation. Baseline for opus 4 vs opus 5.

Elo1,490
SWE-bench72.5%
Out $/1M$75
Model Fact Sheetvs all hub
#9Claude Sonnet 4
Proprietary

First Sonnet 4 generation. Bridge between 3.5/3.7 and Sonnet 5.

Elo1,455
SWE-bench62.8%
Out $/1M$15
Model Fact Sheetvs all hub
#10Claude Haiku 4.5
Proprietary

Anthropic cheap/fast Claude SKU. Official Claude Platform list price $1/$5 per 1M tokens (Anthropic Haiku page).

Elo1,438
SWE-bench58.2%
Out $/1M$5
Model Fact Sheetvs all hub
#11Claude 3.7 Sonnet
Proprietary

Hybrid-reasoning Sonnet from 2025. Kept for historical compare pages.

Elo1,362
SWE-bench70.3%
Out $/1M$15
Model Fact Sheetvs all hub
#12Claude 3.5 Sonnet
Proprietary

2024 workhorse. Still a high-intent compare against GPT-4o.

Elo1,280
SWE-bench49%
Out $/1M$15
Model Fact Sheetvs all hub
#13Claude 3 Opus
Proprietary

Original Claude 3 flagship. Kept so opus 3 vs later Opus and vs GPT-4o still resolve.

Elo1,248
SWE-bench38.4%
Out $/1M$75
Model Fact Sheetvs all hub
#14Claude 3.5 Haiku
Proprietary

Previous cheap Claude. Haiku 4.5 is the current $1/$5 SKU.

Elo1,224
SWE-bench36.2%
Out $/1M$4
Model Fact Sheetvs all hub
#15Claude Opus 5 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-5:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$12.5
Model Fact Sheetvs all hub
#16Anthropic: Claude Sonnet 5 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-sonnet-5:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$5
Model Fact Sheetvs all hub
#17Anthropic: Claude Fable 5 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-fable-5:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$25
Model Fact Sheetvs all hub
#18Anthropic: Claude Opus 4.8 (Fast)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.8-fast). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$50
Model Fact Sheetvs all hub
#19Anthropic: Claude Opus 4.8 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.8:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$12.5
Model Fact Sheetvs all hub
#20Anthropic: Claude Opus 4.7 (Fast)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.7-fast). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$150
Model Fact Sheetvs all hub
#21Anthropic: Claude Opus 4.7
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.7). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$25
Model Fact Sheetvs all hub
#22Anthropic: Claude Opus 4.7 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.7:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$12.5
Model Fact Sheetvs all hub
#23Anthropic: Claude Sonnet 4.6
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-sonnet-4.6). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$15
Model Fact Sheetvs all hub
#24Anthropic: Claude Sonnet 4.6 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-sonnet-4.6:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$7.5
Model Fact Sheetvs all hub
#25Anthropic: Claude Opus 4.6 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.6:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$12.5
Model Fact Sheetvs all hub
#26Anthropic: Claude Opus 4.5 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.5:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$12.5
Model Fact Sheetvs all hub
#27Anthropic: Claude Haiku 4.5 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-haiku-4.5:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$2.5
Model Fact Sheetvs all hub
#28Anthropic: Claude Sonnet 4.5 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-sonnet-4.5:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$7.5
Model Fact Sheetvs all hub
#29Anthropic: Claude Opus 4.1
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.1). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$75
Model Fact Sheetvs all hub
#30Anthropic: Claude Opus 4.1 (batch)
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-opus-4.1:batch). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$37.5
Model Fact Sheetvs all hub
#31Anthropic: Claude 3 Haiku
Proprietary

Auto-discovered from OpenRouter (anthropic/claude-3-haiku). Preview until a second source matches.

Elo—
SWE-bench—
Out $/1M$1.25
Model Fact Sheetvs all hub