Model comparison
Claude 3 Sonnet vs Gemma 7B
Gemma 7B is the stronger model overall, scoring 30.0 to 29.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Gemma 7B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 7B leads 31.2 to 10.7.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Gemma 7B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.0 | 30.0 |
| Released | 2024-02-29 | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3 Sonnet: 29.6 (#302), Gemma 7B: 30.5 (#294)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Coding | 1223 | 1048 |
| HumanEval+ | 64% | 28.7% |
| MBPP+ | 69.3% | 43.4% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
Reasoning Too close to call
Claude 3 Sonnet: 20.5 (#237), Gemma 7B: 19.9 (#249)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1042 |
| Epoch Capabilities Index | 120.7 | 111.99 |
| WinoGrande | 75.1% | 79% |
| DTBench | 53.6% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
Math Gemma 7B leads
Claude 3 Sonnet: 10.7 (#310), Gemma 7B: 31.2 (#228)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Math | 1213 | 1066 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
| GSM8K | — | 46.4% |
Knowledge Gemma 7B leads
Claude 3 Sonnet: 21.1 (#276), Gemma 7B: 27.3 (#252)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Expert | 1173 | 1001 |
| MMLU | 75.9% | 66.1% |
| GPQA Diamond | 40.6% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Gemma 7B: —
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), Gemma 7B: 25.1 (#287)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1205 | 999 |
| LMArena Chinese | 1189 | 1035 |
| LMArena French | 1229 | 1025 |
| LMArena Russian | 1227 | 993 |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 62.8 (#235), Gemma 7B: 51.5 (#295)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1199 | 1017 |
Long Context Claude 3 Sonnet leads
Claude 3 Sonnet: 36.7 (#228), Gemma 7B: 31.1 (#282)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1211 | 1022 |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.1 (#238), Gemma 7B: 27.1 (#302)
| Benchmark | Claude 3 Sonnet | Gemma 7B |
|---|---|---|
| LMArena Text | 1218 | 1056 |
| LMArena Creative Writing | 1186 | 1024 |
| LMArena Multi-Turn | 1227 | 963 |
Frequently asked questions
Is Claude 3 Sonnet better than Gemma 7B?
Gemma 7B is the stronger model overall, scoring 30.0 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Gemma 7B better for coding?
They score almost the same on coding (29.6 vs 30.5); test both on your own repository before choosing.
How many benchmarks do Claude 3 Sonnet and Gemma 7B share?
18 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemma 7B has 27.