Model comparison
Qwen2.5 7B Instruct vs Qwen3-1.7B
Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 26.6 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 0 categories and Qwen3-1.7B in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-1.7B leads 19.2 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Qwen2.5 7B Instruct and 8.1% for Qwen3-1.7B.
Side by side
| Qwen2.5 7B Instruct | Qwen3-1.7B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.0 | 26.6 |
| Released | 2024-09 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.17 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 15 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen2.5 7B Instruct: 36.5 (#208), Qwen3-1.7B: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3-1.7B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Too close to call
Qwen2.5 7B Instruct: 23.8 (#124), Qwen3-1.7B: 24.7 (#115)
| Benchmark | Qwen2.5 7B Instruct | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |
| BALROG | 7.8% | — |
Reasoning Qwen3-1.7B leads
Qwen2.5 7B Instruct: 14.8 (#322), Qwen3-1.7B: 19.2 (#267)
| Benchmark | Qwen2.5 7B Instruct | Qwen3-1.7B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
| Epoch Capabilities Index | 118.51 | — |
Math Qwen3-1.7B leads
Qwen2.5 7B Instruct: 12.6 (#306), Qwen3-1.7B: 16.3 (#294)
| Benchmark | Qwen2.5 7B Instruct | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 8.1% |
| Omni-MATH | 29.4% | — |
Knowledge Qwen3-1.7B leads
Qwen2.5 7B Instruct: 17.0 (#286), Qwen3-1.7B: 19.6 (#278)
| Benchmark | Qwen2.5 7B Instruct | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | 35.5% | 38% |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| MMLU | 72.9% | — |
Instruction Following Not comparable
Qwen2.5 7B Instruct: 63.2 (#231), Qwen3-1.7B: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3-1.7B |
|---|---|---|
| IFEval | 74.1% | — |
Writing & Preference Not comparable
Qwen2.5 7B Instruct: 48.8 (#195), Qwen3-1.7B: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3-1.7B |
|---|---|---|
| WildBench | 73.1% | — |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen3-1.7B?
Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 26.6 on the Noometry Index.
How many benchmarks do Qwen2.5 7B Instruct and Qwen3-1.7B share?
3 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen3-1.7B has 4.