Model comparison
Gemini 2.0 Flash (Feb 2025) vs Gemma 3 12B
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 34.8 to 31.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
GoogleSummary
- They share 17 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 6 categories and Gemma 3 12B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 36.1 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 16.7% for Gemma 3 12B.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B | |
|---|---|---|
| Provider | ||
| Noometry Index | 34.8 | 31.8 |
| Released | 2024-12-06 | 2025-03-12 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 54 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 12B leads
Gemini 2.0 Flash (Feb 2025): 28.2 (#308), Gemma 3 12B: 31.2 (#276)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1351 | 1281 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| SciCode | — | 17.4% |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.0 (#85), Gemma 3 12B: 25.3 (#101)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
| TheAgentCompany | 11.4% | — |
Reasoning Too close to call
Gemini 2.0 Flash (Feb 2025): 15.2 (#308), Gemma 3 12B: 15.2 (#307)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1346 | 1309 |
| DTBench | 63.2% | 48.8% |
| Epoch Capabilities Index | 135.36 | 123.49 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 4.5% |
| LiveBench | 66.9% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.1 (#127), Gemma 3 12B: 21.0 (#273)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 16.7% |
| LMArena Math | 1351 | 1307 |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#207), Gemma 3 12B: 26.5 (#250)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | 64.1% | 39.5% |
| LMArena Expert | 1340 | 1248 |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 4.4% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 35.9 (#74), Gemma 3 12B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
| MindCube | — | 46.7% |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.6 (#144), Gemma 3 12B: 45.9 (#160)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1342 | 1318 |
| LMArena German | 1354 | 1370 |
| LMArena Russian | 1351 | 1335 |
| LMArena Chinese | 1373 | — |
| LMArena French | 1390 | — |
| LMArena Japanese | 1293 | — |
| LMArena Korean | 1314 | — |
| LMArena Spanish | 1363 | — |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.6 (#91), Gemma 3 12B: 68.8 (#179)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1336 | 1299 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Gemma 3 12B leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#198), Gemma 3 12B: 40.0 (#157)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1345 | 1317 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.8 (#184), Gemma 3 12B: 47.7 (#205)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1354 | 1334 |
| LMArena Creative Writing | 1340 | 1331 |
| EQ-Bench Creative Writing | 1128 | 1126 |
| LMArena Multi-Turn | 1350 | 1334 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Gemma 3 12B?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 34.8 to 31.8 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Gemma 3 12B better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.2 versus 28.2 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Gemma 3 12B share?
17 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Gemma 3 12B has 24.