Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Jamba 1.5 Large | Qwen3 235B A22B (Reasoning) |
|---|---|---|
| Input ($/M tokens) | $2 | $0.7 |
| Output ($/M tokens) | $8 | $8.4 |
Verdict. Qwen3 235B A22B (Reasoning) takes the aggregate benchmark matchup 1–0 across 1 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.
Pricing. Both models sit in the mid-tier bracket for output-token pricing. At 1.0× the per-million-token cost, Jamba 1.5 Large is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Jamba 1.5 Large makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Jamba 1.5 Large is strongest on Intelligence Index (4.8). Qwen3 235B A22B (Reasoning) leads on Intelligence Index (13.5).
Speed. Speed data is incomplete for this pair; benchmark and price should decide.
Provider. AI21 Labs and Alibaba sell to overlapping but distinct developer audiences: AI21 Labs tends to ship frontier reasoning models with premium positioning, while Alibaba often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Jamba 1.5 Large costs $180.00 ($2160/year); Qwen3 235B A22B (Reasoning) costs $147.00 ($1764/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Jamba 1.5 Large ≈ $26.00/run, Qwen3 235B A22B (Reasoning) ≈ $20.30/run. At agent/realtime scale (200M input / 100M output per million requests): Jamba 1.5 Large ≈ $1200/run, Qwen3 235B A22B (Reasoning) ≈ $980/run. Qwen3 235B A22B (Reasoning) becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Data from Artificial Analysis API — 12 benchmarks
Qwen3 235B A22B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $2.63/M tokens vs $3.50/M for Jamba 1.5 Large.
Qwen3 235B A22B (Reasoning) wins 1 out of 12 benchmarks compared to 0 for Jamba 1.5 Large. See the detailed benchmark chart above for per-category results.
Qwen3 235B A22B (Reasoning) generates tokens faster at 61 tok/s vs — tok/s. However, Qwen3 235B A22B (Reasoning) has lower time-to-first-token (2.73s vs —s).
Choose based on your priorities: Qwen3 235B A22B (Reasoning) for lower cost, Qwen3 235B A22B (Reasoning) for stronger benchmark performance, and Qwen3 235B A22B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.