#22Alibaba· released 2026-02-09

Qwen: Qwen3 Max Thinking.

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...

View on OpenRouter ↗
Context
262K
Input $/1M
$0.78
Output $/1M
$3.90
Modality
text
Arena Elo
1548
LMArena — human blind votes
AA Index
57.0
Artificial Analysis composite
LiveBench
81.9
Contamination-resistant
GPQA
84.1%
Grad-level science reasoning
MMLU-Pro
85.1%
Broad knowledge
SWE-bench
68.4%
Real GitHub bugs (Verified)
Terminal-Bench
58.7%
Agentic shell tasks
ARC-AGI
26.8%
Abstract reasoning
Aider Polyglot
77.4%
Multi-language code editing
Speed
71 tok/s
Median output speed

Profile

Qwen: Qwen3 Max Thinking 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. 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