score
Qwen3 14B (Non-reasoning) scores 7 (estimated) on the Artificial Analysis Intelligence Index, …
vs class avg: 6
Intelligence, Performance & Price Analysis
score
Qwen3 14B (Non-reasoning) scores 7 (estimated) on the Artificial Analysis Intelligence Index, …
vs class avg: 6
output tokens/sec
Qwen3 14B (Non-reasoning) generates output at 61.5 tokens per second (based on Alibaba's API), …
TTFT
Qwen3 14B (Non-reasoning) has a time to first token (TTFT) of 2. …
/ 1M tokens
Qwen3 14B (Non-reasoning) costs $0.35 per 1M input tokens (at the higher end, median: $0.15) and $1. …
/ 1M tokens
Qwen3 14B (Non-reasoning) costs $0.35 per 1M input tokens (at the higher end, median: $0.15) and $1. …
Ethen's intelligence-driven routing assessment for this model
Overall verdict
Budget-friendly / task-specific model
Best for high-volume, simple, or domain-specific tasks where cost or speed matters more than deep reasoning.
Routing recommendation
Cheaper routes for predictable extraction, labeling, or summarization
Cache-backed reuse for repeated prompts
Cost pressure
Moderate pricing — $0.35 / M input, $1.40 / M output. Costs are manageable, but volume should still be reviewed.
Use this model where capability pays for itself; route away where volume, latency, or budget dominate.
| Use case | Fit | Reason | Routing note |
|---|---|---|---|
| Complex reasoning & agentic workflows | Weak | Intelligence score 7 is better suited for straightforward tasks than multi-step reasoning. | Avoid routing complex agentic tasks to this model. |
| High-volume chat & customer-facing | Strong | Output speed 61.5 tokens/sec is adequate for chat. | Suitable for chat; monitor latency under concurrent load. |
| Latency-sensitive applications | Moderate | TTFT 2.74s — latency may be noticeable in interactive use. | Consider routing latency-critical paths to faster models. |
| Cost-sensitive pipelines | Strong | Output pricing at $1.40 is reasonable for moderate volume. | Suitable for production; review costs as volume grows. |
Cost pressure
MediumPricing is moderate — input $0.35, output $1.40. Costs accumulate at volume but are manageable for valuable tasks.
Key benchmark results at a glance.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Qwen3 14B (Non-reasoning) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Qwen3 14B (Non-reasoning) generates output at 61.5 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Context, Cost & Pricing
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Pricing is moderate — input $0.35, output $1.40. Costs accumulate at volume but are manageable for valuable tasks.
Benchmark scores and quality indices measuring model capability.
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Output tokens per second and generation throughput.
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Time to first token and end-to-end response latency.
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Context window size, cost per task, and token pricing.
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Model size, parameters, and architectural details.
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
Chart source and provenance are listed in Methodology & sources below.
Qwen3 14B (Non-reasoning) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6). Qwen3 14B (Non-reasoning) generates output at 61.5 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Qwen3 14B (Non-reasoning) costs $0.35 per 1M input tokens (at the higher end, median: $0.15) and $1.40 per 1M output tokens (at the higher end, median: $0.32), based on Alibaba's API.
This page is rendered from the normalized profile and page JSON for Qwen3 14B.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.