Model comparison
Qwen2.5 14B Instruct vs Qwen3-1.7B
Qwen3-1.7B has enough public results to be ranked (#336); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Side by side
| Qwen2.5 14B Instruct | Qwen3-1.7B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 26.6 |
| Released | 2024-09 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $1.40 | — |
| Results tracked | 3 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen2.5 14B Instruct: 37.7 (#191), Qwen3-1.7B: —
| Benchmark | Qwen2.5 14B Instruct | Qwen3-1.7B |
|---|---|---|
| BigCodeBench Instruct | 39.8% | — |
| BigCodeBench Complete | 52.2% | — |
Agentic & Tool Use Not comparable
Qwen2.5 14B Instruct: —, Qwen3-1.7B: 24.7 (#115)
| Benchmark | Qwen2.5 14B Instruct | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |
Reasoning Not comparable
Qwen2.5 14B Instruct: —, Qwen3-1.7B: 19.2 (#267)
| Benchmark | Qwen2.5 14B Instruct | Qwen3-1.7B |
|---|---|---|
| Chess Puzzles | — | 0% |
Math Not comparable
Qwen2.5 14B Instruct: —, Qwen3-1.7B: 16.3 (#294)
| Benchmark | Qwen2.5 14B Instruct | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
Knowledge Not comparable
Qwen2.5 14B Instruct: —, Qwen3-1.7B: 19.6 (#278)
| Benchmark | Qwen2.5 14B Instruct | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
| MMLU | 79.9% | — |
Frequently asked questions
Is Qwen2.5 14B Instruct better than Qwen3-1.7B?
Qwen3-1.7B has enough public results to be ranked (#336); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.
How many benchmarks do Qwen2.5 14B Instruct and Qwen3-1.7B share?
0 benchmarks have published results for both models. Qwen2.5 14B Instruct has 3 scored results on Noometry and Qwen3-1.7B has 4.