Model comparison
Sonar vs Step 3.7 Flash
Sonar is the stronger model overall, scoring 38.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.4× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in math, where Step 3.7 Flash leads 42.9 to 33.7.
- Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $1 / $1 for Sonar.
- Step 3.7 Flash accepts more context: 256K tokens versus 128K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.
Side by side
| Sonar | Step 3.7 Flash | |
|---|---|---|
| Provider | Perplexity | StepFun |
| Noometry Index | 38.5 | 37.3 |
| Released | 2024-01-01 | 2026-05-29 |
| Weights | Proprietary | Open |
| Context window | 128K | 256K |
| Max output | 4K | 256K |
| Input $ / M tokens | $1 | $0.18 |
| Output $ / M tokens | $1 | $1.11 |
| Results tracked | 7 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
Sonar: 35.7 (#221), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Sonar | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| LiveBench Coding | 35.1% | — |
| ALE-Bench | — | 694.12 |
Reasoning Too close to call
Sonar: 21.1 (#227), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Sonar | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| LiveBench Reasoning | 46.3% | — |
| LiveBench Data Analysis | 37.9% | — |
| LiveBench | 46.9% | — |
Math Step 3.7 Flash leads
Sonar: 33.7 (#200), Step 3.7 Flash: 42.9 (#82)
| Benchmark | Sonar | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| LiveBench Math | 41.6% | — |
Instruction Following Not comparable
Sonar: 71.4 (#150), Step 3.7 Flash: —
| Benchmark | Sonar | Step 3.7 Flash |
|---|---|---|
| LiveBench Instruction Following | 76.2% | — |
Writing & Preference Not comparable
Sonar: 52.6 (#167), Step 3.7 Flash: —
| Benchmark | Sonar | Step 3.7 Flash |
|---|---|---|
| LiveBench Language | 44.1% | — |
Frequently asked questions
Is Sonar better than Step 3.7 Flash?
Sonar is the stronger model overall, scoring 38.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.4× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Which is cheaper, Sonar or Step 3.7 Flash?
Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Sonar lists at $1 and $1.
Is Sonar or Step 3.7 Flash better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Step 3.7 Flash does, with 256K tokens against 128K.
How many benchmarks do Sonar and Step 3.7 Flash share?
0 benchmarks have published results for both models. Sonar has 7 scored results on Noometry and Step 3.7 Flash has 5.