Model comparison
Sonar vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 37.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Perplexity
StepFunSummary
- The widest gap is in reasoning, where Step 3 leads 27.6 to 20.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Sonar | Step 3 | |
|---|---|---|
| Provider | Perplexity | StepFun |
| Noometry Index | 37.8 | 39.9 |
| Released | 2024-01-01 | — |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Sonar: 35.1 (#217), Step 3: 39.5 (#144)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LiveBench Coding | 35.1% | — |
| LMArena Coding | — | 1367 |
Reasoning Step 3 leads
Sonar: 20.3 (#221), Step 3: 27.6 (#102)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 46.3% | — |
| LMArena Hard Prompts | — | 1355 |
| LiveBench Data Analysis | 37.9% | — |
| LiveBench | 46.9% | — |
Math Step 3 leads
Sonar: 31.3 (#197), Step 3: 34.9 (#148)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LiveBench Math | 41.6% | — |
| LMArena Math | — | 1366 |
Knowledge Not comparable
Sonar: —, Step 3: 36.2 (#161)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Sonar: —, Step 3: 34.9 (#81)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
Sonar: —, Step 3: 46.5 (#154)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Too close to call
Sonar: 71.5 (#146), Step 3: 70.6 (#159)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LiveBench Instruction Following | 76.2% | — |
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Sonar: —, Step 3: 40.3 (#152)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Step 3 leads
Sonar: 52.6 (#166), Step 3: 54.5 (#146)
| Benchmark | Sonar | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |
| LiveBench Language | 44.1% | — |
Frequently asked questions
Is Sonar better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 37.8 on the Noometry Index.
Is Sonar or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 35.1 in the Noometry coding category.
How many benchmarks do Sonar and Step 3 share?
0 benchmarks have published results for both models. Sonar has 7 scored results on Noometry and Step 3 has 17.