LIVETracking 994 AI models from 267 providers.
Beta
Home/Models/Qwen 3.5 Plus (hosted 397B-A17B)
Alibaba Qwen logo

Qwen 3.5 Plus (hosted 397B-A17B)

by Alibaba Qwen · Released Jan 2024

Open Source
42.0
avg score
Rank #165
Compare
Better than 40% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Open Source
Benchmarks
7 tested
Data updated today
About

Tested on 7 benchmarks with 34.8% average. Top scores: OTIS Mock AIME 2024-2025 (85.0%), GPQA diamond (78.9%), SimpleQA Verified (26.0%).

Capabilities
math
36.0
#139 globally
knowledge
40.6
#179 globally
agentic
13.6
#33 globally
Benchmark Scores
Compare All
Tested on 7 benchmarks · Ranked across 3 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
mathCompare math →
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

85.0—
FrontierMath-2025-02-28-Private

Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.

21.0—
FrontierMath-Tier-4-2025-07-01-Private

Hardest tier of FrontierMath. Problems at the frontier of human mathematical ability, many unsolved by most mathematicians.

2.1—
knowledgeCompare knowledge →
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

78.9—
SimpleQA Verified

Simple factual questions with verified correct answers. Tests accuracy of basic knowledge retrieval. Low scores indicate hallucination.

26.0—
Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

17.0—
agenticCompare agentic →
APEX-Agents

Agent performance evaluation testing multi-step tool use, planning, and execution in realistic environments.

13.6—
Quick compare:DeepSeek logovs R1 Distill Qwen 32BGoogle DeepMind logovs Gemma 2 2b ItMeta logovs Llama 3 8B Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
DeepSeek logo
R1 Distill Qwen 32B
DeepSeek
42.2$0.29/1M
Google DeepMind logo
Gemma 2 2b It
Google DeepMind
41.8TBD
Meta logo
Llama 3 8B Instruct
Meta
41.8$0.14/1M
Links
Info
Alibaba QwenPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Alibaba Qwen
Source Code
GitHubHugging Face
BenchGecko API
qwen-3-5-plus-hosted-397b-a17b
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
Alibaba Qwen logoAlibaba QwenTBD
Categories
mathknowledgeagentic
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
DeepSeek logoR1 Distill Qwen 32B
42.2
Google DeepMind logoGemma 2 2b It
41.8
Meta logoLlama 3 8B Instruct
41.8
Anthropic logoClaude 2
41.8
Qwen 3.5 Plus (hosted 397B-A17B) is an open-source text AI model by Alibaba Qwen, released in January 2024. It has an average benchmark score of 42.0.

Related Models

R1 Distill Qwen 32B · DeepSeekGemma 2 2b It · Google DeepMindLlama 3 8B Instruct · MetaClaude 2 · AnthropicClaude Sonnet 4 · Anthropic

Benchmarks

OTIS Mock AIME 2024-2025GPQA diamondSimpleQA VerifiedFrontierMath-2025-02-28-PrivateChess Puzzles

Related Pages

Alibaba Qwen · ProviderAlibaba Qwen · EconomyAll ModelsCompare ModelsPricingDevelopers · API