Model comparison
Qwen3-1.7B vs Qwen3-4B
Qwen3-4B is the stronger model overall, scoring 31.5 to 26.2 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Qwen3-1.7B scores higher in 0 categories and Qwen3-4B in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.1% for Qwen3-1.7B and 52.2% for Qwen3-4B.
Side by side
| Qwen3-1.7B | Qwen3-4B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 26.2 | 31.5 |
| Released | 2025-04-29 | 2025-04-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 4 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Agentic & Tool Use Qwen3-4B leads
Qwen3-1.7B: 24.5 (#108), Qwen3-4B: 27.3 (#94)
| Benchmark | Qwen3-1.7B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.4% | 35.7% |
Reasoning Too close to call
Qwen3-1.7B: 18.5 (#263), Qwen3-4B: 18.5 (#264)
| Benchmark | Qwen3-1.7B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 0% | 4% |
Math Qwen3-4B leads
Qwen3-1.7B: 15.4 (#288), Qwen3-4B: 28.5 (#228)
| Benchmark | Qwen3-1.7B | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.1% | 52.2% |
| MathArena Final-Answer Competitions | — | 38.5% |
Knowledge Qwen3-4B leads
Qwen3-1.7B: 19.6 (#273), Qwen3-4B: 33.0 (#198)
| Benchmark | Qwen3-1.7B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 38% | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
Frequently asked questions
Is Qwen3-1.7B better than Qwen3-4B?
Qwen3-4B is the stronger model overall, scoring 31.5 to 26.2 on the Noometry Index.
How many benchmarks do Qwen3-1.7B and Qwen3-4B share?
4 benchmarks have published results for both models. Qwen3-1.7B has 4 scored results on Noometry and Qwen3-4B has 6.