Model comparison
Gemini 2.5 Flash-Lite vs Gemma 3 27B
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 30.5 on the Noometry Index. Gemma 3 27B costs 1.8× less per token, which makes it the better buy when Gemini 2.5 Flash-Lite's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 8 categories and Gemma 3 27B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemini 2.5 Flash-Lite leads 38.0 to 22.1.
- The biggest single-benchmark swing is Fiction.LiveBench: 47.2% for Gemini 2.5 Flash-Lite and 33.3% for Gemma 3 27B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.10 / $0.40 for Gemini 2.5 Flash-Lite.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 131K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Gemma 3 27B | |
|---|---|---|
| Provider | ||
| Noometry Index | 36.4 | 30.5 |
| Released | 2025-06-17 | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.10 | $0.08 |
| Output $ / M tokens | $0.40 | $0.16 |
| Results tracked | 33 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 38.0 (#167), Gemma 3 27B: 22.1 (#329)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| LMArena Coding | 1373 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| WeirdML | 35.2% | — |
| LiveBench Coding | — | 39.9% |
| ALE-Bench | 325.9 | — |
Agentic & Tool Use Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 27.8 (#89), Gemma 3 27B: 24.9 (#105)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 29.5% |
Reasoning Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 21.5 (#196), Gemma 3 27B: 16.3 (#297)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 40.4% |
| LMArena Hard Prompts | 1377 | 1340 |
| DTBench | 62.8% | 52.5% |
| LMCA | 18.1% | 12.3% |
| Epoch Capabilities Index | 133.93 | 130.04 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| LiveBench Data Analysis | — | 51.5% |
| LiveBench | — | 50% |
Math Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 35.5 (#144), Gemma 3 27B: 24.4 (#261)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| LMArena Math | 1373 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| Omni-MATH | 48% | — |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |
Knowledge Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 32.1 (#206), Gemma 3 27B: 25.4 (#256)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 7.4% |
| LMArena Expert | 1373 | 1303 |
| GPQA Diamond | — | 47.7% |
| MMLU-Pro | 53.7% | — |
| Confabulations | — | 40.3% |
| GPQA (HELM) | 30.9% | — |
Multimodal Gemma 3 27B leads
Gemini 2.5 Flash-Lite: 28.6 (#109), Gemma 3 27B: 32.0 (#94)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| LMArena Vision | 1198 | 1165 |
| GeoBench | — | 52% |
| VPCT | 30% | — |
Multilingual Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 49.5 (#129), Gemma 3 27B: 47.0 (#150)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1369 | 1334 |
| LMArena Chinese | 1404 | 1347 |
| LMArena French | 1388 | 1368 |
| LMArena German | 1390 | 1362 |
| LMArena Japanese | 1359 | 1287 |
| LMArena Korean | 1358 | 1308 |
| LMArena Russian | 1373 | 1349 |
| LMArena Spanish | 1396 | 1348 |
Instruction Following Too close to call
Gemini 2.5 Flash-Lite: 70.2 (#163), Gemma 3 27B: 70.8 (#155)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1366 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
| IFEval | 81% | — |
Long Context Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 33.3 (#257), Gemma 3 27B: 27.6 (#288)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| Fiction.LiveBench | 47.2% | 33.3% |
| LMArena Longer Query | 1373 | 1333 |
Writing & Preference Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 57.0 (#130), Gemma 3 27B: 52.7 (#161)
| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1379 | 1358 |
| LMArena Creative Writing | 1366 | 1346 |
| LMArena Multi-Turn | 1367 | 1344 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| WildBench | 81.8% | — |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Gemma 3 27B?
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 30.5 on the Noometry Index. Gemma 3 27B costs 1.8× less per token, which makes it the better buy when Gemini 2.5 Flash-Lite's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or Gemma 3 27B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Gemini 2.5 Flash-Lite lists at $0.10 and $0.40.
Is Gemini 2.5 Flash-Lite or Gemma 3 27B better for coding?
Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 2.5 Flash-Lite and Gemma 3 27B share?
25 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Gemma 3 27B has 43.