Model comparison
Claude 3.7 Sonnet vs Gemma 3 12B
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 31.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 8 categories and Gemma 3 12B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 35.7 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 16.7% for Gemma 3 12B.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Gemma 3 12B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.4 | 31.8 |
| Released | 2025-02-24 | 2025-03-12 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 58 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 41.1 (#120), Gemma 3 12B: 31.2 (#276)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1361 | 1281 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| SciCode | — | 17.4% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.9 (#46), Gemma 3 12B: 25.3 (#101)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.7 (#252), Gemma 3 12B: 15.2 (#307)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1309 |
| Epoch Capabilities Index | 141.16 | 123.49 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 48.8% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 4.5% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 35.7 (#137), Gemma 3 12B: 21.0 (#273)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 16.7% |
| LMArena Math | 1336 | 1307 |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), Gemma 3 12B: 26.5 (#250)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | 79.7% | 39.5% |
| LMArena Expert | 1321 | 1248 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 4.4% |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.1 (#90), Gemma 3 12B: —
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| MindCube | — | 46.7% |
| SpatialViz-Bench | 33.9% | — |
Multilingual Gemma 3 12B leads
Claude 3.7 Sonnet: 44.3 (#174), Gemma 3 12B: 45.9 (#160)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1296 | 1318 |
| LMArena German | 1301 | 1370 |
| LMArena Russian | 1311 | 1335 |
| LMArena Chinese | 1299 | — |
| LMArena French | 1302 | — |
| LMArena Japanese | 1268 | — |
| LMArena Korean | 1249 | — |
| LMArena Spanish | 1299 | — |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 73.1 (#120), Gemma 3 12B: 68.8 (#179)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1352 | 1299 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Gemma 3 12B: 40.0 (#157)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1373 | 1317 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.6 (#145), Gemma 3 12B: 47.7 (#205)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1314 | 1334 |
| LMArena Creative Writing | 1332 | 1331 |
| EQ-Bench Creative Writing | 1412 | 1126 |
| LMArena Multi-Turn | 1339 | 1334 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Gemma 3 12B?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 31.8 on the Noometry Index.
Is Claude 3.7 Sonnet or Gemma 3 12B better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 31.2 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Gemma 3 12B share?
16 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Gemma 3 12B has 24.