Compare AI Models
Select up to 4 models to compare side by side.
Qwen: Qwen3 235B A22B Instruct 2507
|
|
|---|---|
| Overview | |
| Provider | Qwen |
| Our Score | 56 |
| Performance Tier | Specialist |
| Best For | — |
| Released | Jul 2025 |
| Knowledge Cutoff | — |
| Dimension Scores | |
| Intelligence | 5.0 / 10 |
| Technical | 4.0 / 10 |
| Content | 5.5 / 10 |
| Value | 8.3 / 10 |
| Pricing | |
| Input / 1M tokens | $0.07 |
| Output / 1M tokens | $0.10 |
| Performance | |
| Context Window | 262K |
| Throughput (tok/s) | — |
| Latency (TTFT ms) | — |
| Parameters | 235B |
| Intelligence Indices (Artificial Analysis) | |
| Intelligence | 29.5 |
| Coding | 23.2 |
| Math | 91 |
| Agentic | 33.4 |
| Benchmarks | |
| MMLU-Pro | 0.8 |
| MMLU | — |
| GPQA Diamond | 0.8 |
| GPQA (HF) | — |
| LiveCodeBench | 0.8 |
| HumanEval | — |
| MATH-500 | 1 |
| AIME '25 | 0.9 |
| AIME | 0.9 |
| MATH (HF) | — |
| Humanity's Last Exam | 0.2 |
| SWE-bench | — |
| IFBench | 0.5 |
| IFEval | — |
| Capabilities | |
| Tool Use | ✓ Yes |
| Function Calling | ✓ Yes |
| Vision | ✗ No |
| Open Source | ✗ No |
| License | — |
Looking for the full rankings? View the AI Model Leaderboard or try the Price Calculator to estimate monthly costs.
