#03Alibaba· released 2026-09-23

Qwen: Qwen3.8 Max Prime.

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

View on OpenRouter ↗
Context
1.0M
Input $/1M
$4.00
Output $/1M
$12.00
Modality
text · image · video
Arena Elo
1629
LMArena — human blind votes
AA Index
75.0
Artificial Analysis composite
LiveBench
89.6
Contamination-resistant
GPQA
89.7%
Grad-level science reasoning
MMLU-Pro
89.4%
Broad knowledge
SWE-bench
77.8%
Real GitHub bugs (Verified)
Terminal-Bench
64.8%
Agentic shell tasks
ARC-AGI
21.6%
Abstract reasoning
Aider Polyglot
83.4%
Multi-language code editing
Speed
83 tok/s
Median output speed

Profile

Qwen: Qwen3.8 Max Prime is Alibaba's entry at position #3 on the current aggregated leaderboard. Its strongest signals are human preference voting, graduate-level science reasoning, real-world software engineering, and unattended agentic work. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard