Qwen3.7 Plus (Alibaba Cloud)

Qwen3.7 Plus is a proprietary large language model developed by Alibaba Cloud in collaboration with the Qwen Team, positioned within the Qwen3.7 family as a tier below the flagship Qwen3.7 Max variant. Independent benchmark aggregators list Qwen3.7 Plus under the Alibaba Cloud / Qwen Team attribution, distinguishing it clearly from the separate Max-tier sibling. The model is treated as a closed-weights commercial offering, in contrast to several other Qwen3.x releases that carry explicit open-weights tags on the same leaderboards.

On the multilingual MMLU-ProX reasoning benchmark, Qwen3.7 Plus posts a score of 0.854, placing just behind its Max sibling at 0.870 and ahead of the prior-generation Qwen3.6 Plus at 0.847, which suggests a measured step forward in cross-language academic reasoning rather than a leap. The same aggregator surfaces Qwen3.7 Plus on VITA-Bench alongside other Qwen3.x entries, reinforcing its standing as a general-purpose reasoning and assistant model rather than a narrowly specialized system. Practically, this positions the model as a balanced option for organizations already invested in the Qwen ecosystem that want Plus-tier latency and cost characteristics while retaining competitive multilingual reasoning performance.

LLM Gatewayalibaba/qwen3.7-plusqwen

Open provider page Provider docs

Quick Info

Provider: LLM Gateway
Model key: alibaba/qwen3.7-plus
Release date: Jun 2, 2026
Last updated: Jun 2, 2026
Knowledge cutoff: 2025-04
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.40
Output token cost: $1.60

Limits

Output tokens: 65,536 tokens
Context window: 983,616 tokens

Transparent token rates

Compare Qwen3.7 Plus (Alibaba Cloud) pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Qwen3.7 Plus (Alibaba Cloud)

LLM Gateway

CoverageBenchmark

The LLMBoard Include leaderboard (updated Sep 24, 2026) explicitly lists Qwen3.7-Plus as a model attributed to "Alibaba Cloud / Qwen Team," with a Score of 83.00% and a percentile of 86.67% among 31 participants, ranking it 5th overall as of Sep 23, 2026. It sits behind Claude Opus 4.8 (87.60%), Qwen3.7 Max (86.20%), Q This is independent third-party benchmark evidence rather than a product announcement or provider claim, so it serves as corroboration that the Qwen3.7-Plus variant is publicly tracked and ranked on a general benchmark as of late September 2026. The relatively low "Evidence C" rating noted on the leaderboard indicates

LLM Gateway

CoverageBenchmark

The LLMBoard MMLU-Pro leaderboard (updated Sep 24, 2026) explicitly lists Qwen3.7-Plus as an entry attributed to "Alibaba Cloud / Qwen Team," scoring 88.50% and tying with Qwen3.6 Plus for 3rd–4th place (percentile 97.87% and 98.58% respectively) among 100 evaluated models. Qwen3.7-Plus trails Sakana Namazu (90.33%) an This third-party benchmark snapshot provides recent independent corroboration that the Qwen3.7-Plus variant name is real and continues to be measured alongside other frontier models as of late September 2026. The "Evidence C" rating again signals limited methodology transparency, so the absolute score should be treated

LLM Gateway

CoverageBenchmark

ATLABYTE's benchmark aggregator (data updated September 6, 2026, sourced from llm-stats.com) explicitly lists "Qwen3.7-Plus" attributed to Alibaba Cloud / Qwen Team, scoring 90.3% on GPQA and 77.7% on SWE-bench Verified, placing it among top proprietary models on its GPQA leaderboard alongside Qwen3.7 Max (92.4% GPQA / This third-party benchmark compilation provides secondary, model-focused performance evidence for Qwen3.7-Plus rather than a first-party Alibaba release announcement, and the page does not address LLM Gateway hosting; pricing and context-window fields for the model are not shown in the excerpt.