Alibaba Cloud / Qwen Team model product
Qwen3 14B
Qwen3 14B is a large language model from Alibaba Cloud / Qwen Team.
Updated Oct 23, 2026. Default version: Qwen3 14B
LLMBoard Score27.4Qwen3 14B
Coverage80%17 benchmark families
Context window41KTokens
Official input price$0.35Alibaba API
Qwen3 14B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 14B Benchmark Results
Benchmark scores for Qwen3 14B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAlignBench | Score85.60% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score91.70% | Rank03 | Participants27 | Percentile92.31% | EvidenceC | Evaluated |
| BenchmarkAutoLogi | Score89.20% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkRULER | Score90.10% | Rank03 | Participants5 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkZebraLogic | Score88.50% | Rank07 | Participants9 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkBFCL-v3 | Score70.40% | Rank10 | Participants20 | Percentile52.63% | EvidenceC | Evaluated |
| BenchmarkLiveBench 20241125 | Score71.30% | Rank10 | Participants15 | Percentile35.71% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score96.80% | Rank12 | Participants33 | Percentile65.63% | EvidenceC | Evaluated |
| BenchmarkCreative Writing v3 | Score80.30% | Rank13 | Participants14 | Percentile7.69% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score74.80% | Rank13 | Participants25 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkC-Eval | Score86.20% | Rank14 | Participants20 | Percentile31.58% | EvidenceC | Evaluated |
| BenchmarkWritingBench | Score78.00% | Rank15 | Participants16 | Percentile6.67% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score58.87% | Rank17 | Participants20 | Percentile15.79% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score88.60% | Rank31 | Participants50 | Percentile38.78% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score79.30% | Rank32 | Participants54 | Percentile41.51% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score85.40% | Rank40 | Participants70 | Percentile43.48% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score55.67% | Rank54 | Participants96 | Percentile44.21% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score30.67% | Rank79 | Participants89 | Percentile11.36% | EvidenceB | EvaluatedN/A |
| BenchmarkAIME 2025 | Score70.40% | Rank95 | Participants122 | Percentile22.31% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score40.54% | Rank113 | Participants168 | Percentile32.93% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score0.00% | Rank152 | Participants200 | Percentile24.12% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score60.40% | Rank159 | Participants199 | Percentile20.20% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score15.28% | Rank166 | Participants201 | Percentile17.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score4.53% | Rank168 | Participants200 | Percentile16.08% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score0.00% | Rank183 | Participants193 | Percentile5.21% | EvidenceB | EvaluatedN/A |
Qwen3 14B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Qwen3 14B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.35 input, $1.4 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.076 input, $0.228 output per 1M via DevPass (LLM Gateway)
- Tracked offerings
- 6
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3-14b | Regionglobal | Input / 1M$0.076 | Output / 1M$0.228 | Context32.8K | Updated |
| ProviderNanoGPT | Provider model IDqwen/qwen3-14b | Regionglobal | Input / 1M$0.08 | Output / 1M$0.24 | Context41K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3-14b | Regionglobal | Input / 1M$0.12 | Output / 1M$0.24 | Context41K | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen-3-14b | Regionglobal | Input / 1M$0.12 | Output / 1M$0.24 | Context41K | Updated |
| ProviderAlibaba (China) | Provider model IDqwen3-14b | Regionglobal | Input / 1M$0.144 | Output / 1M$0.574 | Context131.1K | Updated |
| ProviderAlibaba | Provider model IDqwen3-14b | Regionglobal | Input / 1M$0.35 | Output / 1M$1.4 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3 14B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 14B. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 14B Specifications
Technical details for the model's default version.
- Version
- Qwen3 14B
- Released
- Apr 28, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 14B
- Context window
- 41K
- Max output
- 41K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3 14B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen3 14B | Released | LLMBoard27.35 | Parameters14B | Context41K | Max output41K | Open weightsYes | LicenseApache 2.0 |
Models similar to Qwen3 14B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 VL 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 8B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 32B
Alibaba Cloud / Qwen Team
AC
Qwen3 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 30B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3.5 4B
Alibaba Cloud / Qwen Team
What is Qwen3 14B?
Key information about Qwen3 14B and its available data.
Qwen3 14B is part of the Qwen3 series of large language models, which includes dense and mixture-of-experts (MoE) models. The Qwen3 series is trained for reasoning, instruction-following, agent capabilities, and multilingual support.
Data as of 2026-10-22.
FAQ
Common questions about Qwen3 14B.
When was Qwen3 14B released?
Qwen3 14B's default version was released on Apr 28, 2025.
How much does Qwen3 14B cost?
Qwen3 14B's official API price is $0.35 per million input tokens and $1.4 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.076 input and $0.228 output via DevPass (LLM Gateway).
Who created Qwen3 14B?
Qwen3 14B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 14B?
The default version has a 41K token context window.
Is Qwen3 14B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Qwen3 14B?
6 provider offerings are linked to the default version.