All benchmarks
Alibaba Qwen · China · Released 2025-09
Qwen3-Max
Alibaba's flagship trillion-parameter Qwen3 tier — strong multilingual, coding and agentic performance.
Access
open-weights
Context
262,144 tokens
Modalities
text, vision
Languages
100+
Benchmark scores
MMLU
86.0%
Massive Multitask Language Understanding
GPQA
70.0%
Graduate-level science QA (Diamond)
HumanEval
90.2%
Python code completion
SWE-bench
N/A
Real GitHub issue resolution (Verified)
LiveCodeBench
N/A
Contamination-free coding
AIME
85.0%
American Invitational Mathematics Exam
MMMU
N/A
Multimodal college-level reasoning
MATH
88.0%
Competition-level math word problems
Scores as reported by the vendor or leading public leaderboards. "N/A" means the score has not been publicly disclosed for this metric.
Explain like I'm 5
A very big open model that speaks tons of languages and codes well.
Key features
- MoE trillion-scale
- Vision variant
- Agent tools
- Multilingual
Strengths
- Multilingual coverage
- Open ecosystem
- Strong coding
Limitations
- Vision only in specific variants
Best for
Multilingual assistantsEnterprise RAGAgentic apps
Related models
OpenAI
GPT-5
OpenAI's flagship reasoning + multimodal model with a unified router that switches between fast and deep-thinking modes.
Anthropic
Claude Sonnet 4.5
Anthropic's best coding + agentic model, purpose-built for long-horizon computer-use and software engineering tasks.
Google DeepMind
Gemini 2.5 Pro
Google's most capable model with native 1M-token context and full multimodal I/O across text, images, audio and video.
xAI
Grok 4
xAI's frontier reasoning model with real-time X data grounding and a heavy multi-agent variant (Grok 4 Heavy).