ApertureAug 2026
FieldCompareLabsGuideMethod
  • Field
  • Compare
  • Labs
  • Guide
Anthropic
A

Claude Mythos 5

Jul 2026 · Restricted · Restricted · supported evidence

Anthropic’s limited-access peak. Tops composite boards, but you cannot buy it on the public API. Treat Fable 5 as the available twin.

Open compareLab site

Intelligence

63.4

AA Index

API price

$10 / $50

Input / output per 1M

Context

1M

Speed unlisted

Capability

Intelligence Index63.4
Coding index78
Agentic index58
Arena Elo (offset)—

Use it when

  • ▸Eval research
  • ▸Internal Anthropic-class workloads

Skip if

  • –You need a generally available API

Benchmarks

GPQA Diamond
Graduate-level science questions designed so Google search is not enough. Still one of the cleanest knowledge/reasoning splits.
94.1%
Humanity’s Last Exam
Expert-written questions across fields. Harder than MMLU; the current differentiator for “does this model actually know things.”
64.7%
MMLU-Pro
Harder, less-saturated successor to MMLU. Classic MMLU is above 90% for every flagship and no longer ranks the field.
—
SWE-bench Verified
500 human-validated GitHub issues. Score swings 5–15 points by harness — treat vendor numbers as an upper bound.
93.9%
SWE-bench Pro
Harder, contamination-resistant coding eval. Currently the best public split between “can code” and “can maintain a repo.”
80.3%
Terminal-Bench 2.1
End-to-end tasks in a real terminal. Better proxy for coding agents than HumanEval, which is fully saturated.
—
ARC-AGI-2
Abstract visual puzzles. Rewards generalization over memorization. GPT-5.6 Sol currently leads the published set.
—
AIME 2025
American Invitational Mathematics Examination. Contest math; reasoning-mode models dominate.
—
MMMU
College-level multimodal understanding across diagrams, charts, and exam figures.
—

Restricted access as of August 2026.

Modalities

text · vision · tools

Reasoning mode

hybrid

Hybrid and reasoning models spend tokens thinking. That raises GPQA and agents, and also raises latency and bill.

Close on intelligence

  • AClaude Fable 562.1
  • AClaude Opus 563.1
  • OGPT-5.6 Sol60.9

Same lab

  • Claude Fable 5
  • Claude Opus 5
  • Claude Sonnet 5
  • Claude Opus 4.8

Aperture is a field guide, not a vendor. Scores compiled 28 Aug 2026.

MethodologyHow to pick