Model comparison
Phi 3 Small 8k Instruct vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 29.3 on the Noometry Index.
Last verified . 7 shared benchmarks.
Microsoft
PerplexitySummary
- They share 7 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 0 categories and Sonar in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Sonar leads 52.6 to 31.1.
- The biggest single-benchmark swing is LiveBench Language: 12.9% for Phi 3 Small 8k Instruct and 44.1% for Sonar.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Small 8k Instruct | Sonar | |
|---|---|---|
| Provider | Microsoft | Perplexity |
| Noometry Index | 29.3 | 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 | 32 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Phi 3 Small 8k Instruct: 27.9 (#318), Sonar: 35.7 (#221)
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LiveBench Coding | 20.3% | 35.1% |
| LMArena Coding | 1101 | — |
Reasoning Sonar leads
Phi 3 Small 8k Instruct: 14.8 (#323), Sonar: 21.1 (#227)
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LiveBench Reasoning | 15.9% | 46.3% |
| LiveBench Data Analysis | 30.3% | 37.9% |
| LiveBench | 24% | 46.9% |
| LMArena Hard Prompts | 1100 | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| HellaSwag | 77% | — |
| WinoGrande | 81.5% | — |
Math Sonar leads
Phi 3 Small 8k Instruct: 27.6 (#248), Sonar: 33.7 (#200)
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LiveBench Math | 17.6% | 41.6% |
| LMArena Math | 1151 | — |
Knowledge Not comparable
Phi 3 Small 8k Instruct: 29.1 (#240), Sonar: —
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LMArena Expert | 1067 | — |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Not comparable
Phi 3 Small 8k Instruct: 28.5 (#272), Sonar: —
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LMArena Non-English | 1058 | — |
| LMArena Chinese | 1061 | — |
| LMArena French | 1135 | — |
| LMArena German | 1080 | — |
| LMArena Japanese | 966 | — |
| LMArena Korean | 894 | — |
| LMArena Russian | 1111 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Sonar leads
Phi 3 Small 8k Instruct: 51.9 (#292), Sonar: 71.4 (#150)
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LiveBench Instruction Following | 47.2% | 76.2% |
| LMArena Instruction Following | 1087 | — |
Long Context Not comparable
Phi 3 Small 8k Instruct: 33.0 (#267), Sonar: —
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LMArena Longer Query | 1088 | — |
Writing & Preference Sonar leads
Phi 3 Small 8k Instruct: 31.1 (#284), Sonar: 52.6 (#167)
| Benchmark | Phi 3 Small 8k Instruct | Sonar |
|---|---|---|
| LiveBench Language | 12.9% | 44.1% |
| LMArena Text | 1110 | — |
| LMArena Creative Writing | 1083 | — |
| LMArena Multi-Turn | 1068 | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 29.3 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 27.9 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Sonar share?
7 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Sonar has 7.