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.
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.