Model comparison
Gemma 4 31B IT vs Nova 2 Lite
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
GoogleSummary
- They share 15 benchmarks with published results for both. Gemma 4 31B IT scores higher in 6 categories and Nova 2 Lite in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 4 31B IT leads 53.8 to 47.1.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
- Nova 2 Lite accepts more context: 1M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Nova 2 Lite | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 43.5 | 39.7 |
| Released | 2026-04-02 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 33K | 64K |
| Input $ / M tokens | $0.09 | $0.30 |
| Output $ / M tokens | $0.34 | $2.50 |
| Results tracked | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), Nova 2 Lite: 40.7 (#134)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1459 | 1385 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Nova 2 Lite: 24.1 (#121)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Too close to call
Gemma 4 31B IT: 27.2 (#122), Nova 2 Lite: 27.5 (#118)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1364 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Nova 2 Lite: 37.5 (#156)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1465 | 1359 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Nova 2 Lite leads
Gemma 4 31B IT: 37.9 (#151), Nova 2 Lite: 43.0 (#94)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 5.1% |
| LMArena Expert | 1465 | 1358 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Nova 2 Lite: —
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Nova 2 Lite: 47.1 (#153)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1431 | 1337 |
| LMArena Chinese | 1476 | 1364 |
| LMArena French | 1435 | 1381 |
| LMArena Russian | 1460 | 1343 |
| LMArena Spanish | 1444 | 1373 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1271 |
| LMArena Korean | — | 1284 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Nova 2 Lite: 70.5 (#161)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1433 | 1335 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Nova 2 Lite: 40.6 (#150)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1446 | 1335 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Nova 2 Lite: 53.9 (#154)
| Benchmark | Gemma 4 31B IT | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1443 | 1362 |
| LMArena Creative Writing | 1415 | 1291 |
| LMArena Multi-Turn | 1452 | 1338 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Nova 2 Lite?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.7 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Nova 2 Lite?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.
Is Gemma 4 31B IT or Nova 2 Lite better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 40.7 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Nova 2 Lite share?
15 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Nova 2 Lite has 19.