Compare models
Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.
Claude Haiku 4.5Qwen3.5-9B (batch)
| Claude Haiku 4.5 Anthropic | Qwen3.5-9B (batch) Alibaba (Qwen) | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $0.17 |
| Output $/1M | $5.00 | $0.25 |
| Blended $/1M (3:1) | $2.00 | $0.19 |
| Cache read $/1M | $0.10 | — |
| Cache write $/1M | $1.25 | — |
| Quality indices | ||
| Intelligence Index | 16.9 | 13.7 |
| Coding Index | 43.9 | 28.7 |
| Math Index | — | — |
| Agentic Index | 8 | — |
| Speed & latency | ||
| Output speed (tok/s) | — | 69 |
| Time to first token | — | 0.78s |
| Time to first answer token | — | 29.67s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | — | 80.6% |
| Humanity's Last Exam | — | 14.9% |
| IFBench | — | 66.7% |
| AA-LCR (Long Context Reasoning) | — | 70.0% |
| Terminal-Bench Hard | — | 24.2% |
| Terminal-Bench 2.1 | — | 29.2% |
| τ²-Bench (Telecom) | — | 86.8% |
| τ³-Bench Banking | — | 7.0% |
| Design Arena (Elo) | ||
| Website | 1,135 | — |
| UI components | 1,115 | — |
| Data viz | 1,139 | — |
| SVG | 1,049 | — |
| 3D | 1,101 | — |
| Game dev | 1,120 | — |
| Code categories | 1,130 | — |
| ASCII art | 1,159 | — |
| Specs | ||
| Context window | 200K | 262K |
| Max output tokens | 64K | 236K |
| Input modalities | text, image, file | text, image, video |
| Tokenizer | Claude | Qwen3 |