Qwen3-14B
| Released | 2025-04-29 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 40.5 · rank 188 |
| Provider | Alibaba |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 40.5 | 188 | 7 |
| Overall: Coding | 38.9 | 192 | 5 |
| Overall: Reasoning | 44.7 | 162 | 4 |
| Overall: Agentic work | 39.6 | 190 | 5 |
| Overall: Frontend | 37.9 | 182 | 1 |
| Coding | 37.9 | 182 | 1 |
| Agents | 39.7 | 159 | 1 |
| Reasoning | 42.3 | 172 | 3 |
| Math | 47.9 | 131 | 1 |
| General | 38.7 | 165 | 1 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 40.5 ±2.4 | 7 |
| Non-reasoning | 39.7 ±5.7 | 2 |
Evidence
Coding 37.9 ±4.7
Agents 39.7 ±3.6
Reasoning 42.3 ±4.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 63.8% | Epoch AI | 2026-08-28 |
| CritPt | 0.0% | Epoch AI | 2026-11-11 |
| Kagi Reasoning Benchmark | 49.1% | Kagi | 2026-11-11 |
Math 47.9 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | Epoch AI | 2026-08-28 |
General 38.7 ±5.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Longform Creative Writing | 35.9% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| BFCL v4 | 37.8% | BFCL | A stronger configuration result was used |
| GPQA Diamond | 53.4% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 25.8% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-14b