Model comparison
Phi 3 Mini 4k Instruct vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 27.9 on the Noometry Index.
Last verified . 7 shared benchmarks.
Microsoft
PerplexitySummary
- They share 7 benchmarks with published results for both. Phi 3 Mini 4k 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 27.6.
- The biggest single-benchmark swing is LiveBench Instruction Following: 39.1% for Phi 3 Mini 4k Instruct and 76.2% for Sonar.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Mini 4k Instruct | Sonar | |
|---|---|---|
| Provider | Microsoft | Perplexity |
| Noometry Index | 27.9 | 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 | 35 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Sonar: 35.7 (#221)
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LiveBench Coding | 15.5% | 35.1% |
| LMArena Coding | 1093 | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Sonar leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Sonar: 21.1 (#227)
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LiveBench Reasoning | 26.8% | 46.3% |
| LiveBench Data Analysis | 34.7% | 37.9% |
| LiveBench | 22.4% | 46.9% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1072 | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| WinoGrande | 70.8% | — |
Math Sonar leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Sonar: 33.7 (#200)
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LiveBench Math | 15.7% | 41.6% |
| LMArena Math | 1111 | — |
Knowledge Not comparable
Phi 3 Mini 4k Instruct: 28.5 (#246), Sonar: —
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LMArena Expert | 1045 | — |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Not comparable
Phi 3 Mini 4k Instruct: 26.3 (#280), Sonar: —
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LMArena Non-English | 1021 | — |
| LMArena Chinese | 1021 | — |
| LMArena French | 1076 | — |
| LMArena German | 1044 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
| LMArena Russian | 1022 | — |
| LMArena Spanish | 1085 | — |
Instruction Following Sonar leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Sonar: 71.4 (#150)
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LiveBench Instruction Following | 39.1% | 76.2% |
| LMArena Instruction Following | 1053 | — |
Long Context Not comparable
Phi 3 Mini 4k Instruct: 31.7 (#276), Sonar: —
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LMArena Longer Query | 1044 | — |
Writing & Preference Sonar leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Sonar: 52.6 (#167)
| Benchmark | Phi 3 Mini 4k Instruct | Sonar |
|---|---|---|
| LiveBench Language | 9.2% | 44.1% |
| LMArena Text | 1073 | — |
| LMArena Creative Writing | 1037 | — |
| LMArena Multi-Turn | 1018 | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Sonar share?
7 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Sonar has 7.