Model comparison
Gemini 3.1 Flash Lite vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 40.4 on the Noometry Index.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 2 categories and Gemma 4 31B IT in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 4 31B IT leads 41.9 to 37.5.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 70.6% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.25 / $1.50 for Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Gemma 4 31B IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 40.4 | 43.2 |
| Released | 2026-03-03 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.25 | $0.09 |
| Output $ / M tokens | $1.50 | $0.34 |
| Results tracked | 38 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemini 3.1 Flash Lite: 37.5 (#179), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1256 | 1364 |
| SciCode | 41.9% | 43.4% |
| WeirdML | 52.2% | 52.3% |
| LMArena Coding | 1400 | 1459 |
| ALE-Bench | 797.73 | 925.5 |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 29.9 (#72), Gemma 4 31B IT: —
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
Reasoning Gemma 4 31B IT leads
Gemini 3.1 Flash Lite: 22.3 (#181), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 63.5% |
| NYT Connections (extended) | 8.2% | 70.6% |
| CritPt | 1.1% | 1.4% |
| Chess Puzzles | 25% | 5% |
| Thematic Generalization | 63.3% | 53% |
| LMArena Hard Prompts | 1407 | 1448 |
| DTBench | 76.8% | 82.7% |
| LMCA | 35% | 39.3% |
| Epoch Capabilities Index | 144.45 | 142.74 |
| EnigmaEval | 3% | — |
| Surface Evolver Bench | — | 30.6% |
| ForecastBench | 54.4 | — |
Math Gemma 4 31B IT leads
Gemini 3.1 Flash Lite: 39.5 (#82), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 73.3% |
| LMArena Math | 1427 | 1464 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.7 (#95), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 81.8% | 75.8% |
| Vectara Hallucination Rate | 8.2% | 7.4% |
| LMArena Expert | 1397 | 1465 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 10.4% |
Multimodal Gemma 4 31B IT leads
Gemini 3.1 Flash Lite: 38.7 (#57), Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1240 | 1278 |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
Gemini 3.1 Flash Lite: 52.5 (#82), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1410 | 1431 |
| LMArena Chinese | 1461 | 1478 |
| LMArena French | 1423 | 1436 |
| LMArena Russian | 1420 | 1462 |
| LMArena Spanish | 1420 | 1443 |
| LMArena German | 1429 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1393 | — |
Instruction Following Gemma 4 31B IT leads
Gemini 3.1 Flash Lite: 72.9 (#126), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1376 | 1433 |
Long Context Gemma 4 31B IT leads
Gemini 3.1 Flash Lite: 42.5 (#117), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1394 | 1446 |
Writing & Preference Too close to call
Gemini 3.1 Flash Lite: 61.0 (#90), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Gemini 3.1 Flash Lite | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1416 | 1443 |
| LMArena Creative Writing | 1401 | 1416 |
| LMArena Multi-Turn | 1417 | 1452 |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 40.4 on the Noometry Index.
Which is cheaper, Gemini 3.1 Flash Lite or Gemma 4 31B IT?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Gemini 3.1 Flash Lite lists at $0.25 and $1.50.
Is Gemini 3.1 Flash Lite or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.1 Flash Lite and Gemma 4 31B IT share?
30 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Gemma 4 31B IT has 35.