CompareLLM.ai
Live
Leaderboard
Models
Compare
Best of & Stacks
Research & News
…
CompareLLM.ai
Precision Benchmarks

Programmatic, dated AI model benchmarks, head-to-head comparisons, and Stack Engine presets.

Daily ingest · 06:00 UTC

Analytics & Benchmarks

  • AI Model Leaderboard
  • Head-to-Head Compare Hub
  • Models Directory
  • Stack Engine Presets
  • Frontier Models
  • Open Weights Catalog

Guides & Intent Lists

  • Best LLM Lists (2026)
  • Best Coding LLM
  • Best Cheap LLM
  • Fastest Low-Latency LLM
  • Claude vs GPT Benchmark
  • What is Elo?
  • Methodology Guides
  • News & Dispatches

Transparency & API

  • Evaluation Methodology
  • Benchmark Changelog
  • Public JSON API
  • llms.txt Specification
  • Privacy Policy
  • Sign In / Account

© 2026 CompareLLM. Public benchmark data aggregated from Arena Elo, LiveBench, SWE-bench & OpenRouter.

Every score has a dated snapshot.

Theme:
Currency:
  1. Home
  2. Providers
  3. Alibaba
AI Provider Portfolio
8 active models in catalog

Alibaba Models

Comprehensive benchmark scores, coding performance, latency metrics, and API pricing for all models developed by Alibaba.

Flagship ModelQwen 3 Max
Portfolio Avg Elo1454 Elo
Browse Other Providers
AnthropicOpenAIGoogle

Available Models & Verified Benchmarks

#1Qwen 3 Max
Proprietary

Alibaba flagship. Strong math and multilingual code.

Elo1,518
SWE-bench67.8%
Out $/1M$4.8
Model Fact Sheetvs all hub
#2Qwen QwQ 32B
Open Weights

Alibaba specialized open reasoning model competing with frontier closed reasoning models.

Elo1,495
SWE-bench67.5%
Out $/1M$1.2
Model Fact Sheetvs all hub
#3Qwen 2.5 Plus
Proprietary

Alibaba balanced flagship API model with high-throughput general reasoning.

Elo1,445
SWE-bench59.2%
Out $/1M$1
Model Fact Sheetvs all hub
#4Qwen3 235B
Open Weights

Open-weight Qwen3 mixture-of-experts.

Elo1,440
SWE-bench59.4%
Out $/1M$0.88
Model Fact Sheetvs all hub
#5Qwen 2.5 Coder 32B
Open Weights

Alibaba dedicated open-weight code generation model with near-frontier SWE-bench Verified coding capability.

Elo1,425
SWE-bench65.2%
Out $/1M$0.72
Model Fact Sheetvs all hub
#6Qwen3.8 27B
Open Weights

Alibaba open-weight 27B drop dated Aug 14 2026. Dense enough to self-host; not a frontier MoE.

Elo1,398
SWE-bench58.8%
Out $/1M$0.4
Model Fact Sheetvs all hub
#7Qwen Image 2.0 Pro
Proprietary

Alibaba multimodal image synthesis foundation model with strong bilingual Chinese/English typography and cultural asset fidelity.

Elo—
SWE-bench—
Out $/1M—
Model Fact Sheetvs all hub
#8Wan2.6 Text to Image
Open Weights

Alibaba high-efficiency open video/image unified transformer backbone.

Elo—
SWE-bench—
Out $/1M—
Model Fact Sheetvs all hub