Model comparison
Gemma 3 1B vs Qwen2.5 7B Instruct
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 20.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Gemma 3 1B scores higher in 1 category and Qwen2.5 7B Instruct in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen2.5 7B Instruct leads 23.5 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 19.9% for Gemma 3 1B and 35.5% for Qwen2.5 7B Instruct.
Side by side
| Gemma 3 1B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 20.7 | 28.6 |
| Released | 2025-03-12 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 4 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 1B: —, Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | Gemma 3 1B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Qwen2.5 7B Instruct leads
Gemma 3 1B: 13.5 (#144), Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | Gemma 3 1B | Qwen2.5 7B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 7.2% | — |
| BALROG | — | 7.8% |
Reasoning Gemma 3 1B leads
Gemma 3 1B: 18.5 (#260), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | Gemma 3 1B | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.44 |
Math Qwen2.5 7B Instruct leads
Gemma 3 1B: 9.6 (#310), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | Gemma 3 1B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 2.5% |
| Omni-MATH | — | 29.4% |
Knowledge Qwen2.5 7B Instruct leads
Gemma 3 1B: 7.1 (#309), Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | Gemma 3 1B | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 19.9% | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| MMLU | — | 72.9% |
Instruction Following Not comparable
Gemma 3 1B: —, Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | Gemma 3 1B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
Writing & Preference Not comparable
Gemma 3 1B: —, Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | Gemma 3 1B | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |
Frequently asked questions
Is Gemma 3 1B better than Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 20.7 on the Noometry Index.
How many benchmarks do Gemma 3 1B and Qwen2.5 7B Instruct share?
3 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and Qwen2.5 7B Instruct has 15.