Qwen Plus 2025-01-25
Jan 2025
Qwen Plus 2025-01-25Compare inon
Qwen Plus 2025-01-25 measured on 3 of 104 Chat & Knowledge benchmarks3
BenchmarkByScoreRank
Legacy · saturated or no longer reported2
No benchmark matches
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGPT-5.6 Lunamax+90%-25%$0.18
OpenKimi K3max+94%+900%$2.00Sampling parameters are fixed+3
CheaperMiniMax M3unstatedOpen+89%-13%$0.30 / $1.20Deployment status experimental · Self-hostedCheaperGPT-6 Lunamax+88%-67%$0.068Function calling only with none · Chat Completions+3
CheaperGLM 5.3 FlashmaxOpen+87%-60%$0.28Defaults to max · Self-hosted+4ModelScoreCostPer taskWhat changes
GPT-5.6 Lunamax+90%-25%$0.18MiniMax M3unstatedOpen+89%-13%$0.30 / $1.20Deployment status experimental · Self-hostedGPT-6 Lunamax+88%-67%$0.068Function calling only with none · Chat Completions+3GLM 5.3 FlashmaxOpen+87%-60%$0.28Defaults to max · Self-hosted+4
Claude Haiku 5.5max+86%-67%$0.21Remove sampling parameters+5ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow+71%-25%$0.01
Gemini 3.1 Flash Litehigh+70%-6%$0.06GPT-6 Lunamax+88%-67%$0.068Function calling only with none · Chat Completions+3GPT OSS 120BhighOpen+57%-90%$0.092GPT-5.6 Terralow+82%+650%$0.14Prompts with >272K input tokensModelScoreCostPer taskWhat changes
Kimi K3maxOpen+94%+900%$2.00Sampling parameters are fixed+3GLM 5.2maxOpen+91%+258%$1.47
DeepSeek V4 Pro 0813maxOpen+91%+230%$0.67Pass back reasoning_content · Chat Completions+4MiniMax M3unstatedOpen+89%-13%$0.30 / $1.20Deployment status experimental · Self-hostedGLM 5.3maxOpen+89%+258%$2.01Reasoning cannot be disabled+3ModelScoreCostPer taskWhat changes
Qwen3.8 Max (0902)xhigh+92%—$2 / $6Qwen3.7 Maxmax+89%—$1.48 / $4.43Qwen3.6 Plusunstated+84%—$0.50 / $3Qwen3.7 Plusunstated+83%—$0.32 / $1.28Qwen3.6 Max Previewunstated+82%—$1.30 / $7.80Include the word JSON · QwenCloudQwen3.5 397B A17BnoneOpen+80%—$0.60 / $3.60Qwen3.6 27BunstatedOpen+78%—$0.60 / $3.60Qwen3.6 35B A3BnoneOpen+76%—$0.25 / $1.49All Alibaba (Qwen) models →History
10 versionsBenchmarks
in Chat & KnowledgeGPQA Diamond · Epoch48.1#105
MATH Level 565.3#14
OTIS Mock AIME 2024 202517.8#104
FAQ
How much does Qwen Plus 2025-01-25 cost?›
$0.40 per 1M input tokens and $1.20 per 1M output tokens.
Is Qwen Plus 2025-01-25 free to use?›
There is no free API; the cheapest paid price is $0.40 per 1M input tokens.
How good is Qwen Plus 2025-01-25, and what is it best at?›
#105 of 133 in Chat & Knowledge.
Is Qwen Plus 2025-01-25 better than Qwen2.5 72B Instruct?›
On GPQA Diamond · Epoch, Qwen Plus 2025-01-25 scores 48.1 vs 49.1 — lower.
How can I use Qwen Plus 2025-01-25?›
Through the Alibaba (Qwen) API.
When was Qwen Plus 2025-01-25 released? Is there a newer version?›
Released 2025-01-30. It is the current version in its line.
Can Qwen Plus 2025-01-25 read images?›
No, it accepts text only.
What is Qwen Plus 2025-01-25?›
Qwen Plus 2025-01-25 is a language model from Alibaba (Qwen), released Jan 2025.
What are the best alternatives to Qwen Plus 2025-01-25?›
GPT-5.6 Luna (cheaper), Kimi K3 (open weights).