Model comparison
Gemma 7B vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 29.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 27.2.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Gemma 7B | Sonar | |
|---|---|---|
| Provider | Perplexity | |
| Noometry Index | 29.5 | 37.8 |
| Released | 2024-02-21 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 27 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Gemma 7B: 29.9 (#290), Sonar: 35.1 (#217)
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1048 | — |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Sonar leads
Gemma 7B: 19.0 (#247), Sonar: 20.3 (#221)
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1042 | — |
| LiveBench Data Analysis | — | 37.9% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.74 | — |
| HellaSwag | 82.2% | — |
| LiveBench | — | 46.9% |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Sonar leads
Gemma 7B: 28.7 (#225), Sonar: 31.3 (#197)
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1066 | — |
| GSM8K | 46.4% | — |
Knowledge Not comparable
Gemma 7B: 26.8 (#248), Sonar: —
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LMArena Expert | 1002 | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Not comparable
Gemma 7B: 25.3 (#282), Sonar: —
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LMArena Non-English | 999 | — |
| LMArena Chinese | 1035 | — |
| LMArena French | 1024 | — |
| LMArena Russian | 993 | — |
Instruction Following Sonar leads
Gemma 7B: 51.7 (#290), Sonar: 71.5 (#146)
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1017 | — |
Long Context Not comparable
Gemma 7B: 31.1 (#277), Sonar: —
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LMArena Longer Query | 1022 | — |
Writing & Preference Sonar leads
Gemma 7B: 27.2 (#297), Sonar: 52.6 (#166)
| Benchmark | Gemma 7B | Sonar |
|---|---|---|
| LMArena Text | 1056 | — |
| LMArena Creative Writing | 1024 | — |
| LMArena Multi-Turn | 963 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Gemma 7B better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 29.5 on the Noometry Index.
Is Gemma 7B or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.1 versus 29.9 in the Noometry coding category.
How many benchmarks do Gemma 7B and Sonar share?
0 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Sonar has 7.