Model comparison
Gemma 3 27B vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.0 to 30.5 on the Noometry Index. Gemma 3 27B costs 8.5× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Gemma 3 27B scores higher in 2 categories and Nova 2 Lite in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nova 2 Lite leads 40.1 to 22.1.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
- Nova 2 Lite accepts more context: 1M tokens versus 131K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 27B | Nova 2 Lite | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 30.5 | 39.0 |
| Released | 2025-03-11 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 8K | 64K |
| Input $ / M tokens | $0.08 | $0.30 |
| Output $ / M tokens | $0.16 | $2.50 |
| Results tracked | 43 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Gemma 3 27B: 22.1 (#329), Nova 2 Lite: 40.1 (#131)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1322 | 1386 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Too close to call
Gemma 3 27B: 24.9 (#105), Nova 2 Lite: 23.9 (#114)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | 27.1% |
Reasoning Nova 2 Lite leads
Gemma 3 27B: 16.3 (#297), Nova 2 Lite: 26.4 (#120)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1364 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Nova 2 Lite leads
Gemma 3 27B: 24.4 (#261), Nova 2 Lite: 34.8 (#154)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1312 | 1359 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Nova 2 Lite leads
Gemma 3 27B: 25.4 (#256), Nova 2 Lite: 42.5 (#88)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 5.1% |
| LMArena Expert | 1303 | 1360 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
Multimodal Not comparable
Gemma 3 27B: 32.0 (#94), Nova 2 Lite: —
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |
Multilingual Too close to call
Gemma 3 27B: 47.0 (#150), Nova 2 Lite: 47.3 (#148)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1334 | 1337 |
| LMArena Chinese | 1347 | 1364 |
| LMArena French | 1368 | 1381 |
| LMArena German | 1362 | 1343 |
| LMArena Japanese | 1287 | 1273 |
| LMArena Korean | 1308 | 1284 |
| LMArena Russian | 1349 | 1343 |
| LMArena Spanish | 1348 | 1372 |
Instruction Following Too close to call
Gemma 3 27B: 70.8 (#155), Nova 2 Lite: 70.7 (#156)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1321 | 1335 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Nova 2 Lite leads
Gemma 3 27B: 27.6 (#288), Nova 2 Lite: 40.6 (#145)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1333 | 1335 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Nova 2 Lite leads
Gemma 3 27B: 52.7 (#161), Nova 2 Lite: 54.1 (#150)
| Benchmark | Gemma 3 27B | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1358 | 1362 |
| LMArena Creative Writing | 1346 | 1291 |
| LMArena Multi-Turn | 1344 | 1338 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.0 to 30.5 on the Noometry Index. Gemma 3 27B costs 8.5× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or Nova 2 Lite?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.
Is Gemma 3 27B or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 131K.
How many benchmarks do Gemma 3 27B and Nova 2 Lite share?
19 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Nova 2 Lite has 19.