Model comparison
Claude Sonnet 4 vs Gemma 3 4B
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 28.1 on the Noometry Index. Gemma 3 4B costs 120× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Gemma 3 4B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4 leads 41.8 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 7.5% for Gemma 3 4B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Gemma 3 4B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.8 | 28.1 |
| Released | 2025-05-22 | 2025-03-12 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 64K | 4K |
| Input $ / M tokens | $3 | $0.04 |
| Output $ / M tokens | $15 | $0.08 |
| Results tracked | 58 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Gemma 3 4B: 35.9 (#215)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1414 | 1230 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), Gemma 3 4B: 20.9 (#142)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Gemma 3 4B: 13.2 (#335)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| Kagi LLM Benchmark | 73% | 25.2% |
| LMArena Hard Prompts | 1372 | 1253 |
| DTBench | 77.1% | 50.9% |
| LMCA | 29% | 2.8% |
| Epoch Capabilities Index | 141.69 | 116.02 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 3.1% | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Gemma 3 4B: 16.8 (#292)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 7.5% |
| LMArena Math | 1375 | 1239 |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Gemma 3 4B: 11.8 (#299)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | 79.2% | 23.2% |
| Vectara Hallucination Rate | 10.3% | 6.4% |
| LMArena Expert | 1372 | 1223 |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Gemma 3 4B: —
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Gemma 3 4B: 42.5 (#194)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1333 | 1273 |
| LMArena German | 1331 | 1281 |
| LMArena Russian | 1355 | 1294 |
| LMArena Chinese | 1350 | — |
| LMArena French | 1363 | — |
| LMArena Japanese | 1302 | — |
| LMArena Korean | 1291 | — |
| LMArena Spanish | 1357 | — |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Gemma 3 4B: 65.2 (#225)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1376 | 1239 |
| IFEval | 84% | — |
Long Context Gemma 3 4B leads
Claude Sonnet 4: 33.7 (#259), Gemma 3 4B: 38.7 (#194)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1398 | 1273 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Gemma 3 4B: 42.0 (#239)
| Benchmark | Claude Sonnet 4 | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1351 | 1291 |
| LMArena Creative Writing | 1345 | 1271 |
| EQ-Bench Creative Writing | 1483 | 1068 |
| LMArena Multi-Turn | 1376 | 1255 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Gemma 3 4B?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 28.1 on the Noometry Index. Gemma 3 4B costs 120× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or Gemma 3 4B?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Gemma 3 4B better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 131K.
How many benchmarks do Claude Sonnet 4 and Gemma 3 4B share?
20 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemma 3 4B has 22.