Compare AI Models
Select up to 4 models to compare side by side.
Qwen3 VL 4B (Reasoning)
Alibaba
|
|
|---|---|
| Overview | |
| Provider | Alibaba |
| DFO score | 11.5 |
| Performance Tier | Emerging |
| Best For | – |
| Released | Oct 2025 |
| Knowledge Cutoff | – |
| Pricing | |
| Input / 1M tokens | $0.00 |
| Output / 1M tokens | $0.00 |
| Performance | |
| Context Window | 0 |
| Throughput (tok/s) | – |
| Latency (TTFT ms) | – |
| Parameters | – |
| What the boards rank on | |
| Intelligence Index | 7 |
| Coding Index | – |
| Agentic Index | – |
| Arena creative writing | – |
| Arena instruction following | – |
| Benchmarks | |
| Math Index | 25.7 |
| MMLU-Pro | 0.7 |
| GPQA Diamond | 0.5 |
| LiveCodeBench | 0.3 |
| MATH-500 | – |
| AIME '25 | 0.3 |
| AIME | – |
| Humanity's Last Exam | 0 |
| IFBench | 0.4 |
Looking for the full rankings? View the AI Model Leaderboard or try the Price Calculator to estimate monthly costs.