Model comparison
Gemma 3 27B vs Qwen2.5 7B Instruct
Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.0 on the Noometry Index.
Last verified . 6 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Gemma 3 27B scores higher in 6 categories and Qwen2.5 7B Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5 7B Instruct leads 36.5 to 22.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 2.5% for Qwen2.5 7B Instruct.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
Side by side
| Gemma 3 27B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 30.8 | 29.0 |
| Released | 2025-03-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.08 | $0.17 |
| Output $ / M tokens | $0.16 | $0.70 |
| Results tracked | 43 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Gemma 3 27B: 22.5 (#334), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LiveBench Coding | 39.9% | — |
| LMArena Coding | 1322 | — |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Gemma 3 27B leads
Gemma 3 27B: 25.1 (#110), Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
| BALROG | — | 7.8% |
Reasoning Gemma 3 27B leads
Gemma 3 27B: 16.7 (#301), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| DTBench | 52.5% | 47.7% |
| LMCA | 12.3% | 6.4% |
| Epoch Capabilities Index | 130.04 | 118.51 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LMArena Hard Prompts | 1340 | — |
| LiveBench Data Analysis | 51.5% | — |
| LiveBench | 50% | — |
Math Gemma 3 27B leads
Gemma 3 27B: 25.9 (#265), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 2.5% |
| Omni-MATH | — | 29.4% |
| LiveBench Math | 55.4% | — |
| LMArena Math | 1312 | — |
| MATH Level 5 | 74% | — |
Knowledge Gemma 3 27B leads
Gemma 3 27B: 25.5 (#261), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 47.7% | 35.5% |
| MMLU-Pro | — | 53.9% |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1304 | — |
| MMLU | — | 72.9% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Qwen2.5 7B Instruct: —
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Gemma 3 27B: 46.9 (#155), Qwen2.5 7B Instruct: —
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1334 | — |
| LMArena Chinese | 1346 | — |
| LMArena French | 1368 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Russian | 1349 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| LiveBench Instruction Following | 74.9% | — |
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1321 | — |
Long Context Not comparable
Gemma 3 27B: 27.6 (#293), Qwen2.5 7B Instruct: —
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| Fiction.LiveBench | 33.3% | — |
| LMArena Longer Query | 1333 | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Gemma 3 27B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1358 | — |
| LMArena Creative Writing | 1346 | — |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1345 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Qwen2.5 7B Instruct?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.0 on the Noometry Index.
Which is cheaper, Gemma 3 27B or Qwen2.5 7B Instruct?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.
Is Gemma 3 27B or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 27B and Qwen2.5 7B Instruct share?
6 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Qwen2.5 7B Instruct has 15.