Model comparison
Gemini 1.5 Pro (May 2024) vs Gemma 3 12B
Gemini 1.5 Pro (May 2024) and Gemma 3 12B score almost the same on the Noometry Index (32.1 vs 32.1), so choose on price, context window or the category you care about most.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 4 categories and Gemma 3 12B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemma 3 12B leads 25.5 to 17.9.
- The biggest single-benchmark swing is GPQA Diamond: 57.2% for Gemini 1.5 Pro (May 2024) and 39.5% for Gemma 3 12B.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Gemma 3 12B | |
|---|---|---|
| Provider | ||
| Noometry Index | 32.1 | 32.1 |
| Released | 2024-02-15 | 2025-03-12 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 45 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Gemma 3 12B: 31.7 (#280)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1294 | 1281 |
| SciCode | — | 17.4% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Gemma 3 12B leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Gemma 3 12B: 25.5 (#108)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Gemma 3 12B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Gemma 3 12B: 15.7 (#313)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1309 |
| DTBench | 59% | 48.8% |
| Epoch Capabilities Index | 131.73 | 123.5 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LMCA | — | 4.5% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Gemma 3 12B: 22.3 (#279)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 16.7% |
| LMArena Math | 1315 | 1307 |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Gemma 3 12B: 26.5 (#257)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | 57.2% | 39.5% |
| LMArena Expert | 1279 | 1248 |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 4.4% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Gemma 3 12B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
| MindCube | — | 46.7% |
Multilingual Too close to call
Gemini 1.5 Pro (May 2024): 45.3 (#174), Gemma 3 12B: 45.7 (#165)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1312 | 1318 |
| LMArena German | 1286 | 1370 |
| LMArena Russian | 1320 | 1335 |
| LMArena Chinese | 1331 | — |
| LMArena French | 1302 | — |
| LMArena Japanese | 1292 | — |
| LMArena Korean | 1298 | — |
| LMArena Spanish | 1311 | — |
Instruction Following Too close to call
Gemini 1.5 Pro (May 2024): 68.6 (#185), Gemma 3 12B: 68.6 (#186)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1299 |
| IFEval | 83.7% | — |
Long Context Too close to call
Gemini 1.5 Pro (May 2024): 39.8 (#169), Gemma 3 12B: 40.0 (#162)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1308 | 1317 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Gemma 3 12B: 47.5 (#209)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1319 | 1334 |
| LMArena Creative Writing | 1333 | 1331 |
| LMArena Multi-Turn | 1296 | 1334 |
| EQ-Bench Creative Writing | — | 1126 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Gemma 3 12B?
Gemini 1.5 Pro (May 2024) and Gemma 3 12B score almost the same on the Noometry Index (32.1 vs 32.1), so choose on price, context window or the category you care about most.
Is Gemini 1.5 Pro (May 2024) or Gemma 3 12B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 31.7 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Gemma 3 12B share?
16 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Gemma 3 12B has 24.