Model comparison
Gemma 2B vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 24.1.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2B | Sonar | |
|---|---|---|
| Provider | Perplexity | |
| Noometry Index | 29.1 | 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 | 23 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Gemma 2B: 28.9 (#300), Sonar: 35.1 (#217)
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1010 | — |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Sonar leads
Gemma 2B: 17.9 (#275), Sonar: 20.3 (#221)
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 989 | — |
| LiveBench Data Analysis | — | 37.9% |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 93.57 | — |
| HellaSwag | 71.4% | — |
| LiveBench | — | 46.9% |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Sonar leads
Gemma 2B: 27.6 (#237), Sonar: 31.3 (#197)
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1009 | — |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Sonar: —
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Not comparable
Gemma 2B: 23.1 (#289), Sonar: —
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| LMArena Non-English | 958 | — |
| LMArena Chinese | 986 | — |
| LMArena Russian | 937 | — |
Instruction Following Sonar leads
Gemma 2B: 48.8 (#297), Sonar: 71.5 (#146)
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 971 | — |
Long Context Not comparable
Gemma 2B: 29.9 (#286), Sonar: —
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| LMArena Longer Query | 981 | — |
Writing & Preference Sonar leads
Gemma 2B: 24.1 (#303), Sonar: 52.6 (#166)
| Benchmark | Gemma 2B | Sonar |
|---|---|---|
| LMArena Text | 1002 | — |
| LMArena Creative Writing | 986 | — |
| LMArena Multi-Turn | 945 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Gemma 2B better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 29.1 on the Noometry Index.
Is Gemma 2B or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.1 versus 28.9 in the Noometry coding category.
How many benchmarks do Gemma 2B and Sonar share?
0 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Sonar has 7.