Model comparison
phi-3-medium 14B vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
PerplexitySummary
- The widest gap is in math, where Sonar leads 33.7 to 27.3.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| phi-3-medium 14B | Sonar | |
|---|---|---|
| Provider | Microsoft | Perplexity |
| Noometry Index | 29.7 | 38.5 |
| Released | 2024-04-23 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 13 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
phi-3-medium 14B: 36.8 (#201), Sonar: 35.7 (#221)
| Benchmark | phi-3-medium 14B | Sonar |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LiveBench Coding | — | 35.1% |
| BigCodeBench Complete | 48.7% | — |
Reasoning Not comparable
phi-3-medium 14B: —, Sonar: 21.1 (#227)
| Benchmark | phi-3-medium 14B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LiveBench Data Analysis | — | 37.9% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.23 | — |
| HellaSwag | 82.4% | — |
| LiveBench | — | 46.9% |
| WinoGrande | 81.5% | — |
Math Sonar leads
phi-3-medium 14B: 27.3 (#250), Sonar: 33.7 (#200)
| Benchmark | phi-3-medium 14B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| MATH Level 5 | 17.6% | — |
Knowledge Not comparable
phi-3-medium 14B: 9.1 (#306), Sonar: —
| Benchmark | phi-3-medium 14B | Sonar |
|---|---|---|
| GPQA Diamond | 27.6% | — |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Instruction Following Not comparable
phi-3-medium 14B: —, Sonar: 71.4 (#150)
| Benchmark | phi-3-medium 14B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
Writing & Preference Not comparable
phi-3-medium 14B: —, Sonar: 52.6 (#167)
| Benchmark | phi-3-medium 14B | Sonar |
|---|---|---|
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is phi-3-medium 14B better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 29.7 on the Noometry Index.
Is phi-3-medium 14B or Sonar better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 35.7 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Sonar share?
0 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Sonar has 7.