Qwen3-1.7B
| Released | 2025-04-29 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 33.8 (early, few results) |
| Provider | Alibaba |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 33.8 | 3 | |
| Overall: Coding | 33.5 | 2 | |
| Overall: Reasoning | 33.9 | 2 | |
| Overall: Agentic work | 33.6 | 2 | |
| Agents | 33.9 | 1 | |
| Reasoning | 32.8 | 1 | |
| Math | 35.4 | 1 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 33.4 ±5.0 | 2 |
| Non-reasoning | 31.9 ±5.7 | 2 |
Evidence
Agents 33.9 ±3.6
Reasoning 32.8 ±4.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 38.0% | Epoch AI | 2026-08-28 |
Math 35.4 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.1% | Epoch AI | 2026-08-28 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| GPQA Diamond | 30.6% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-1-7b