Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 Coder 480B A35B Instruct | Jamba 1.6 Large |
|---|---|---|
| Input ($/M tokens) | $1.5 | $2 |
| Output ($/M tokens) | $7.5 | $8 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 Coder 480B A35B Instruct is cheaper overall. Its blended price (3:1 input/output ratio) is $3.00/M tokens vs $3.50/M for Jamba 1.6 Large.
Qwen3 Coder 480B A35B Instruct wins 12 out of 12 benchmarks compared to 0 for Jamba 1.6 Large. See the detailed benchmark chart above for per-category results.
Qwen3 Coder 480B A35B Instruct generates tokens faster at 70 tok/s vs 59 tok/s. However, Jamba 1.6 Large has lower time-to-first-token (0.73s vs 1.66s).
Choose based on your priorities: Qwen3 Coder 480B A35B Instruct for lower cost, Qwen3 Coder 480B A35B Instruct for stronger benchmark performance, and Qwen3 Coder 480B A35B Instruct for faster generation. For latency-sensitive apps, check the TTFT comparison above.