Qwen3 14B

qwen/qwen3-14b-04-28

Qwen3 14B is a text-to-text model from Qwen. It supports a context length of 131,072 tokens, tool use, and reasoning.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providerqwen
releasedJan 1, 2024
context41K
input / M$0.12

Specifications

What the API gives you

Context window
41K tokens
Max output
16K tokens
Input price
$0.12 / 1M tokens
Output price
$0.24 / 1M tokens
Cache read
—
Modalities
text → text
Knowledge cutoff
Mar 31, 2025
Released
Jan 1, 2024

Measured evidence

Public benchmark record

BFCL
41.0%2026-10-21
GPQA Diamond (Epoch AI)
63.8% ± 2.92026-08-28evaluated 2026-08-28
OTIS Mock AIME (Epoch AI)‡
25.8% ± 4.82026-08-30none effort, evaluated 2026-08-30
OTIS Mock AIME (Epoch AI)
66.4% ± 6.22026-08-28evaluated 2026-08-28

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Math & ReasoningEstablished evidence

    16% of intended weighted task evidence across 2 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Tool & Function CallingProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Agent Steerability. 6 of 7 configured evaluation feeds currently have results.

Show all 12 tasks
  • Best LLM for Logic & Problem SolvingProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 9 of 9 configured evaluation feeds currently have results.

  • Best LLM for JSON & Schema OutputProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Data Analysis or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Structured Data ExtractionProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Data Analysis or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Computer & Browser UseProvisional evidence

    11% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    11% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FrontierMath Tiers 1-3 (Epoch AI) or LiveBench Mathematics. 6 of 6 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.