Model comparison
gpt-oss-20b vs Step 3.7 Flash
Step 3.7 Flash is the stronger model overall, scoring 36.5 to 32.1 on the Noometry Index. gpt-oss-20b costs 12× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
StepFunSummary
- They share 3 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Step 3.7 Flash in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.7 Flash leads 40.9 to 37.6.
- The biggest single-benchmark swing is SciCode: 34.4% for gpt-oss-20b and 40% for Step 3.7 Flash.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- Step 3.7 Flash accepts more context: 256K tokens versus 131K.
Side by side
| gpt-oss-20b | Step 3.7 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 32.1 | 36.5 |
| Released | 2025-08-05 | 2026-05-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 16K | 256K |
| Input $ / M tokens | $0.018 | $0.18 |
| Output $ / M tokens | $0.09 | $1.11 |
| Results tracked | 34 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
gpt-oss-20b: 37.1 (#185), Step 3.7 Flash: 39.4 (#147)
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| SciCode | 34.4% | 40% |
| ALE-Bench | 566.05 | 694.12 |
| WeirdML | 40.9% | — |
| LMArena Coding | 1307 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Step 3.7 Flash: —
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Step 3.7 Flash leads
gpt-oss-20b: 18.8 (#251), Step 3.7 Flash: 20.9 (#211)
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| CritPt | 1.4% | 2.3% |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 39.7% |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | 1274 | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |
Math Step 3.7 Flash leads
gpt-oss-20b: 37.6 (#93), Step 3.7 Flash: 40.9 (#74)
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
Knowledge Not comparable
gpt-oss-20b: 34.6 (#186), Step 3.7 Flash: —
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
Multilingual Not comparable
gpt-oss-20b: 42.4 (#192), Step 3.7 Flash: —
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1311 | — |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
| LMArena Russian | 1279 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Not comparable
gpt-oss-20b: 62.0 (#235), Step 3.7 Flash: —
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |
Long Context Not comparable
gpt-oss-20b: 37.9 (#203), Step 3.7 Flash: —
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1251 | — |
Writing & Preference Not comparable
gpt-oss-20b: 35.8 (#260), Step 3.7 Flash: —
| Benchmark | gpt-oss-20b | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1288 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is gpt-oss-20b better than Step 3.7 Flash?
Step 3.7 Flash is the stronger model overall, scoring 36.5 to 32.1 on the Noometry Index. gpt-oss-20b costs 12× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Step 3.7 Flash?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.
Is gpt-oss-20b or Step 3.7 Flash better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 39.4 versus 37.1 in the Noometry coding category.
Which has the bigger context window?
Step 3.7 Flash does, with 256K tokens against 131K.
How many benchmarks do gpt-oss-20b and Step 3.7 Flash share?
3 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Step 3.7 Flash has 5.