#22Alibaba· released 2026-08-26

Qwen: Qwen3.8 Flash.

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

View on OpenRouter ↗
Context
1.0M
Input $/1M
$0.15
Output $/1M
$0.47
Modality
text · image · video
Arena Elo
1511
LMArena — human blind votes
AA Index
56.0
Artificial Analysis composite
LiveBench
73.1
Contamination-resistant
GPQA
80.2%
Grad-level science reasoning
MMLU-Pro
82.4%
Broad knowledge
SWE-bench
61.2%
Real GitHub bugs (Verified)
Terminal-Bench
45.8%
Agentic shell tasks
ARC-AGI
16.4%
Abstract reasoning
Aider Polyglot
72.3%
Multi-language code editing
Speed
205 tok/s
Median output speed

Profile

Qwen: Qwen3.8 Flash is Alibaba's entry at position #22 on the current aggregated leaderboard. Its strongest signals are graduate-level science reasoning, real-world software engineering, unattended agentic work, and raw output speed. 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