Model comparison
Claude 3.7 Sonnet vs Gemma 3 27B
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 30.8 on the Noometry Index.
Last verified . 35 shared benchmarks.
GoogleSummary
- They share 35 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 9 categories and Gemma 3 27B in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.3 to 27.6.
- The biggest single-benchmark swing is Aider Polyglot: 64.9% for Claude 3.7 Sonnet and 4.9% for Gemma 3 27B.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Gemma 3 27B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.5 | 30.8 |
| Released | 2025-02-24 | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.16 |
| Results tracked | 58 | 43 |
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: 40.6 (#136), Gemma 3 27B: 22.5 (#334)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| Aider Polyglot | 64.9% | 4.9% |
| LiveBench Coding | 74.5% | 39.9% |
| LMArena Coding | 1361 | 1322 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| SciCode | — | 21.2% |
| GSO | 3.8% | — |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), Gemma 3 27B: 25.1 (#110)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
| 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: 18.6 (#277), Gemma 3 27B: 16.7 (#301)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| LiveBench Reasoning | 87.8% | 43.8% |
| LMArena Hard Prompts | 1333 | 1340 |
| LiveBench Data Analysis | 74% | 51.5% |
| Epoch Capabilities Index | 141.16 | 130.04 |
| LiveBench | 76.1% | 50% |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 40.4% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| EnigmaEval | 4.2% | — |
| DTBench | — | 52.5% |
| LMCA | — | 12.3% |
| ForecastBench | 61.8 | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 37.5 (#153), Gemma 3 27B: 25.9 (#265)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 22.5% |
| LiveBench Math | 79% | 55.4% |
| LMArena Math | 1337 | 1312 |
| MATH Level 5 | 91.2% | 74% |
| Omni-MATH | 33% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.8 (#130), Gemma 3 27B: 25.5 (#261)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 79.7% | 47.7% |
| Confabulations | 14.7% | 40.3% |
| LMArena Expert | 1321 | 1304 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Vectara Hallucination Rate | — | 7.4% |
| GPQA (HELM) | 60.8% | — |
Multimodal Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.7 (#95), Gemma 3 27B: 32.6 (#100)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| LMArena Vision | 1169 | 1164 |
| GeoBench | 68% | 52% |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Gemma 3 27B leads
Claude 3.7 Sonnet: 44.1 (#179), Gemma 3 27B: 46.9 (#155)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1296 | 1334 |
| LMArena Chinese | 1299 | 1346 |
| LMArena French | 1303 | 1368 |
| LMArena German | 1301 | 1362 |
| LMArena Japanese | 1267 | 1287 |
| LMArena Korean | 1249 | 1308 |
| LMArena Russian | 1311 | 1349 |
| LMArena Spanish | 1298 | 1349 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 72.9 (#125), Gemma 3 27B: 70.6 (#160)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 74.9% |
| LMArena Instruction Following | 1352 | 1321 |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Gemma 3 27B: 27.6 (#293)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| Fiction.LiveBench | 83.3% | 33.3% |
| LMArena Longer Query | 1373 | 1333 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.4 (#150), Gemma 3 27B: 52.5 (#168)
| Benchmark | Claude 3.7 Sonnet | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1314 | 1358 |
| LMArena Creative Writing | 1332 | 1346 |
| Short-Story Creative Writing | 81.1% | 79.9% |
| EQ-Bench Creative Writing | 1412 | 1266 |
| LMArena Multi-Turn | 1339 | 1345 |
| LiveBench Language | 59.9% | 34.6% |
| WildBench | 81.4% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Gemma 3 27B?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 30.8 on the Noometry Index.
Is Claude 3.7 Sonnet or Gemma 3 27B better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 22.5 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Gemma 3 27B share?
35 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Gemma 3 27B has 43.