ApertureAug 2026
FieldCompareLabsGuideMethod
  • Field
  • Compare
  • Labs
  • Guide
xAI
x

Grok 4.5

Jul 2026 · Proprietary · Superseded · supported evidence

Five weeks older than 4.6, same list price. Only stay if a SWE-Pro number is load-bearing — 4.6 has not published one.

Open compareLab site

Intelligence

55.8

AA Index

API price

$2 / $6

Input / output per 1M

Context

500K

60 tok/s

Capability

Intelligence Index55.8
Coding index72.4
Agentic index48.9
Arena Elo (offset)151

Use it when

  • ▸SWE-Pro tracked pipelines

Skip if

  • –You can take 4.6’s intelligence bump

Benchmarks

GPQA Diamond
Graduate-level science questions designed so Google search is not enough. Still one of the cleanest knowledge/reasoning splits.
93.4%
Humanity’s Last Exam
Expert-written questions across fields. Harder than MMLU; the current differentiator for “does this model actually know things.”
—
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.
—
SWE-bench Pro
Harder, contamination-resistant coding eval. Currently the best public split between “can code” and “can maintain a repo.”
64.7%
Terminal-Bench 2.1
End-to-end tasks in a real terminal. Better proxy for coding agents than HumanEval, which is fully saturated.
83.3%
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.
—

Modalities

text · vision · tools

Reasoning mode

reasoning

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

Close on intelligence

  • AClaude Sonnet 555.3
  • OGPT-5.6 Terra56.6
  • OGPT-5.6 Luna52.3

Same lab

  • Grok 4.6

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

MethodologyHow to pick