Model comparison
Gemini 2.0 Flash (Feb 2025) vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 35.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
GoogleSummary
- They share 22 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and Gemma 4 31B IT in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 4 31B IT leads 42.3 to 28.4.
- The biggest single-benchmark swing is WeirdML: 25.8% for Gemini 2.0 Flash (Feb 2025) and 52.3% for Gemma 4 31B IT.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 35.1 | 43.5 |
| Released | 2024-12-06 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.09 |
| Output $ / M tokens | — | $0.34 |
| Results tracked | 54 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Gemma 4 31B IT: 42.3 (#108)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| WeirdML | 25.8% | 52.3% |
| LMArena Coding | 1350 | 1459 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1366 |
| SciCode | — | 43.4% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 925.5 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Gemma 4 31B IT: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Gemma 4 31B IT: 27.2 (#122)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 63.5% |
| LMArena Hard Prompts | 1346 | 1448 |
| DTBench | 63.2% | 82.7% |
| Epoch Capabilities Index | 135.36 | 142.74 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| EnigmaEval | 1.1% | — |
| Thematic Generalization | — | 53% |
| LiveBench Reasoning | 78.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| LiveBench | 66.9% | — |
Math Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Gemma 4 31B IT: 43.2 (#81)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 73.3% |
| LMArena Math | 1352 | 1465 |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Gemma 4 31B IT: 37.9 (#151)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 64.1% | 75.8% |
| LMArena Expert | 1339 | 1465 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 10.4% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 7.4% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Gemma 4 31B IT: 41.6 (#34)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1158 | 1277 |
| GeoBench | 77% | — |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Gemma 4 31B IT: 53.8 (#57)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1342 | 1431 |
| LMArena Chinese | 1373 | 1476 |
| LMArena French | 1391 | 1435 |
| LMArena Russian | 1351 | 1460 |
| LMArena Spanish | 1363 | 1444 |
| LMArena German | 1353 | — |
| LMArena Japanese | 1294 | — |
| LMArena Korean | 1313 | — |
Instruction Following Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Gemma 4 31B IT: 75.5 (#61)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1336 | 1433 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Gemma 4 31B IT: 44.2 (#71)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1344 | 1446 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemma 4 31B IT leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Gemma 4 31B IT: 60.5 (#96)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1354 | 1443 |
| LMArena Creative Writing | 1340 | 1415 |
| EQ-Bench Creative Writing | 1128 | 1368 |
| LMArena Multi-Turn | 1350 | 1452 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| EQ-Bench 4 | — | 1120 |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Gemma 4 31B IT share?
22 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Gemma 4 31B IT has 35.