Alibaba (Qwen) · closed · 2026-05

Qwen3.7-Max

Item: Qwen3.7-Max
Rating: 88.9

#1 index 88.9

the take
Frontier scores across the board and hardly anyone in the West is talking about it. Two catches: it is closed weights despite Alibaba's open Qwen line, and it is a token furnace that inflates the real bill.

benchmarks

80.4

92.4

—

97.1

LiveCodeBench (coding)

91.6

specs

Context: 1M
Input: $2.5/M
Output: $7.5/M
Speed: —
Modality: text

strengths

Frontier reasoning, coding and math
1M context, strong agentic behavior
Open-weights sibling line (Qwen3.6) exists

weaknesses

Closed/API-only, unlike the group
Very verbose, inflating effective cost
Text-only

Sources: [1][2]

Back to leaderboard Battle Qwen3.7-Max