Model comparison
Gemini 2.0 Flash (Feb 2025) vs Gemma 2 9B
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 25.9 on the Noometry Index.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 6 categories and Gemma 2 9B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 37.9 to 9.9.
- The biggest single-benchmark swing is LiveBench Reasoning: 78.2% for Gemini 2.0 Flash (Feb 2025) and 15.2% for Gemma 2 9B.
- Gemma 2 9B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B | |
|---|---|---|
| Provider | ||
| Noometry Index | 35.1 | 25.9 |
| Released | 2024-12-06 | 2024-06-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 9B leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Gemma 2 9B: 29.4 (#304)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| BigCodeBench Instruct | 45.9% | 34.7% |
| LiveBench Coding | 63.4% | 22.5% |
| LMArena Coding | 1350 | 1173 |
| BigCodeBench Complete | 59.9% | 40.6% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| WeirdML | 25.8% | — |
| CadEval | 30% | — |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Gemma 2 9B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Too close to call
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Gemma 2 9B: 15.9 (#309)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| LiveBench Reasoning | 78.2% | 15.2% |
| LMArena Hard Prompts | 1346 | 1171 |
| LiveBench Data Analysis | 69.4% | 36.4% |
| Epoch Capabilities Index | 135.36 | 119.83 |
| LiveBench | 66.9% | 28.7% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| EnigmaEval | 1.1% | — |
| DTBench | 63.2% | — |
| PIQA | — | 83.7% |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Gemma 2 9B: 9.9 (#318)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 0.6% |
| LiveBench Math | 75.8% | 19.8% |
| LMArena Math | 1352 | 1183 |
| MATH Level 5 | 82.2% | 21% |
| Omni-MATH | 45.9% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
| GSM8K | — | 84.9% |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Gemma 2 9B: 9.7 (#305)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | 64.1% | 27.5% |
| LMArena Expert | 1339 | 1147 |
| MMLU | 79.7% | 72.1% |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| BoolQ | — | 85.7% |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Gemma 2 9B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Gemma 2 9B: 36.6 (#238)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 1342 | 1188 |
| LMArena Chinese | 1373 | 1185 |
| LMArena French | 1391 | 1190 |
| LMArena German | 1353 | 1186 |
| LMArena Japanese | 1294 | 1144 |
| LMArena Korean | 1313 | 1137 |
| LMArena Russian | 1351 | 1200 |
| LMArena Spanish | 1363 | 1200 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Gemma 2 9B: 57.6 (#269)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 52.6% |
| LMArena Instruction Following | 1336 | 1178 |
| IFEval | 84.1% | — |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Gemma 2 9B: 36.3 (#233)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | 1344 | 1197 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Gemma 2 9B: 32.1 (#281)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1354 | 1207 |
| LMArena Creative Writing | 1340 | 1206 |
| EQ-Bench Creative Writing | 1128 | 841 |
| LMArena Multi-Turn | 1350 | 1193 |
| LiveBench Language | 51.3% | 25.5% |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Gemma 2 9B?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 25.9 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Gemma 2 9B better for coding?
Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Gemma 2 9B share?
32 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Gemma 2 9B has 35.