Model comparison
gpt-oss-20b vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 4.2× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 35.5.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
- Step 3.5 Flash accepts more context: 256K tokens versus 131K.
Side by side
| gpt-oss-20b | Step 3.5 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 32.5 | 42.3 |
| Released | 2025-08-05 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 16K | 256K |
| Input $ / M tokens | $0.018 | $0.10 |
| Output $ / M tokens | $0.09 | $0.30 |
| Results tracked | 34 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
gpt-oss-20b: 37.6 (#192), Step 3.5 Flash: 42.4 (#105)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1306 | 1436 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Step 3.5 Flash: —
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Step 3.5 Flash leads
gpt-oss-20b: 19.3 (#261), Step 3.5 Flash: 22.2 (#202)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1411 |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math Step 3.5 Flash leads
gpt-oss-20b: 39.4 (#103), Step 3.5 Flash: 42.6 (#84)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1317 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge Step 3.5 Flash leads
gpt-oss-20b: 34.6 (#195), Step 3.5 Flash: 39.6 (#132)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1258 | 1421 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Step 3.5 Flash leads
gpt-oss-20b: 42.2 (#197), Step 3.5 Flash: 50.5 (#119)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1268 | 1385 |
| LMArena Chinese | 1314 | 1447 |
| LMArena German | 1255 | 1405 |
| LMArena Japanese | 1244 | 1354 |
| LMArena Korean | 1236 | 1352 |
| LMArena Russian | 1278 | 1385 |
| LMArena Spanish | 1267 | 1419 |
| LMArena French | — | 1421 |
Instruction Following Step 3.5 Flash leads
gpt-oss-20b: 61.8 (#240), Step 3.5 Flash: 73.1 (#124)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1236 | 1385 |
| IFEval | 73.2% | — |
Long Context Step 3.5 Flash leads
gpt-oss-20b: 37.9 (#209), Step 3.5 Flash: 42.8 (#117)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1250 | 1402 |
Writing & Preference Step 3.5 Flash leads
gpt-oss-20b: 35.5 (#265), Step 3.5 Flash: 58.8 (#113)
| Benchmark | gpt-oss-20b | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1287 | 1403 |
| LMArena Creative Writing | 1201 | 1357 |
| LMArena Multi-Turn | 1268 | 1405 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 4.2× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Step 3.5 Flash?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.
Is gpt-oss-20b or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 131K.
How many benchmarks do gpt-oss-20b and Step 3.5 Flash share?
16 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Step 3.5 Flash has 19.