# Qwen4 Max

As of November 22, 2026, Qwen4 Max ranks #33 of 120 models overall with 66.6 ±5.8 on the LLMBenchmark Index. Qwen4 Max ranks #17 of 111 in coding, its strongest category. Qwen4 Max costs $1.425 per million input tokens and $4.275 per million output tokens. Qwen4 Max was released on November 16, 2026.

Page: https://llmbenchmark.ai/models/qwen4-max
Data from November 22, 2026. Every figure below names the board it was read from and the day.

- Maker: Qwen
- Released: November 16, 2026
- Price per million input tokens: $1.425
- Price per million output tokens: $4.275
- Context window: 1M tokens
- Overall rank: 33 of 120, by the LLMBenchmark Index
- LLMBenchmark Index: 66.6 ±5.8 (90% margin, from 3 of 7 inputs)
- Artificial Analysis Intelligence Index: 42.9
- Vibe Coding Index: 74.0 (from 4 of 6 coding benchmarks)

Benchmark results (26 of 222):

- LiveBench coding: 69.8% (source: LiveBench, read November 22, 2026)
- LMArena WebDev: 1751 Elo (xHigh) (source: LMArena WebDev, read November 22, 2026)
- Vals Index: 63.2% (source: Vals Index, read November 22, 2026)
- AA Intelligence Index: 42.9 (source: Artificial Analysis (via OpenRouter), read November 22, 2026)
- LiveBench reasoning: 92.2% (source: LiveBench, read November 22, 2026)
- LiveBench data analysis: 83.4% (source: LiveBench, read November 22, 2026)
- LiveBench research: 84.7% (source: LiveBench, read November 22, 2026)
- LiveBench browser: 80.7% (source: LiveBench, read November 22, 2026)
- LiveBench long agentic: 46.6% (source: LiveBench, read November 22, 2026)
- LiveBench design: 79.1% (source: LiveBench, read November 22, 2026)
- Terminal-Bench 4 (Vals AI): 48.5% (Mini-SWE-agent) (source: Vals AI boards, read November 22, 2026)
- Vibe Code Bench (Vals AI): 86.7% (OpenHands) (source: Vals AI boards, read November 22, 2026)
- Tax Agent Bench (Vals AI): 40.4% (source: Vals AI boards, read November 22, 2026)
- Legal Research Bench (Vals AI): 41.4% (source: Vals AI boards, read November 22, 2026)
- Harvey's Legal Agent Benchmark (Vals AI): 21.3% (source: Vals AI boards, read November 22, 2026)
- Terminal-Bench 4.0 (Artificial Analysis run): 48.5% (source: Artificial Analysis, read November 22, 2026)
- FrontierCode 2.0: 26.5% (source: Artificial Analysis, read November 22, 2026)
- HLE-Diamond (Artificial Analysis run): 44.9% (source: Artificial Analysis, read November 22, 2026)
- GDPval-AA: 1809 Elo (source: Artificial Analysis, read November 22, 2026)
- AA-Omniscience: 27.7 (source: Artificial Analysis, read November 22, 2026)
- CritPt v2, hard subset (Artificial Analysis run): 43.0% (source: Artificial Analysis, read November 22, 2026)
- ALE-Bench: 1831.0 (xHigh) (source: ALE-Bench (Sakana AI), read November 22, 2026)
- LMArena WebDev: React: 1785 Elo (xHigh) (source: LMArena (Hugging Face dataset), read November 22, 2026)
- LMArena WebDev: HTML: 1752 Elo (xHigh) (source: LMArena (Hugging Face dataset), read November 22, 2026)
- LMArena WebDev: from an image: 1675 Elo (xHigh) (source: LMArena (Hugging Face dataset), read November 22, 2026)
- GameBench 2: 82.4 (High) (source: DuelLab GameBench 2, read November 22, 2026)
