ApertureAug 2026
FieldCompareLabsGuideMethod
  • Field
  • Compare
  • Labs
  • Guide
Alibaba (Qwen)
Q

Qwen3.8 Max

Aug 2026 · Open weight · Current · supported evidence

Best open-weight flagship on evidence-backed boards. Slow to sample. Strong multilingual and agentic for the license.

Open compareLab site

Intelligence

58.1

AA Index

API price

$2 / $6

Input / output per 1M

Context

1M

21 tok/s

Capability

Intelligence Index58.1
Coding index71.8
Agentic index58.4
Arena Elo (offset)180

Use it when

  • ▸Open-weight frontier
  • ▸Self-host at scale
  • ▸Chinese + English

Skip if

  • –You need 50+ tok/s from a single replica

Benchmarks

GPQA Diamond
Graduate-level science questions designed so Google search is not enough. Still one of the cleanest knowledge/reasoning splits.
92.7%
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.”
—
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.
—

Modalities

text · vision · tools

2.4T MoE / 95B active

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 Sol60.9
  • OGPT-5.6 Terra56.6

Same lab

  • Qwen3.8 27B
  • Qwen3.8 Flash

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

MethodologyHow to pick