Intelligence Verification

AI & LLM Benchmark Hub

Objective, independently verified performance metrics for the world’s leading generative AI models. Our AI model rankings track LLM benchmarks, coding benchmarks, and image and video generation quality using published evaluation suites — the Artificial Analysis Intelligence Index v4.1, the Artificial Analysis Coding Index, and LMArena community arenas — alongside official API pricing from each provider. Scores are never estimated: every number is verified against its source before it appears here.

Updated July 27, 2026 · Methodology

Compare Models

0 of 3 slots filled

Rank Model & Company AA Index Cost/1M (In/Out) Speed Actions
01 No change data

Claude Opus 5 (Adaptive Reasoning, Max Effort)

Anthropic · claude-opus-5

 60.7 $5 / $25 44 t/s
02 No change data

Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)

Anthropic · claude-opus-5-xhigh

 60.1 $5 / $25 60 t/s
03 2

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

Anthropic · claude-fable-5

 59.9 $10 / $50 58 t/s
04 2

GPT-5.6 Sol (max)

OpenAI · gpt-5-6-sol

 58.9 $5 / $30 74 t/s
05 No change data

Claude Opus 5 (Adaptive Reasoning, High Effort)

Anthropic · claude-opus-5-high

 58.9 $5 / $25 50 t/s
01

Claude Opus 5 (Adaptive Reasoning, Max Effort)

Anthropic

60.7 No change data
Cost/1M (In/Out) $5 / $25
Speed 44 t/s
02

Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)

Anthropic

60.1 No change data
Cost/1M (In/Out) $5 / $25
Speed 60 t/s
03

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

Anthropic

59.9 2
Cost/1M (In/Out) $10 / $50
Speed 58 t/s
04

GPT-5.6 Sol (max)

OpenAI

58.9 2
Cost/1M (In/Out) $5 / $30
Speed 74 t/s
05

Claude Opus 5 (Adaptive Reasoning, High Effort)

Anthropic

58.9 No change data
Cost/1M (In/Out) $5 / $25
Speed 50 t/s

Source: Artificial Analysis Intelligence Index (verified 2026-07-27).

Latest Benchmark Analysis