gpt-oss-20b vs Step 3.7 Flash
Updated October 21, 2026. 11 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
gpt-oss-20b has the edge where output tokens cost 7.7x less, and where what matters is SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 11
- gpt-oss-20b only
- 49
- Step 3.7 Flash only
- 7
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Step 3.7 Flash
Step 3.7 Flash leads, 19.5 against 10.0.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only gpt-oss-20b has a GPQA Diamond result, 68.9%.
Directional only
Math
AIME
No call
Only gpt-oss-20b has a AIME result, 86.0%.
Directional only
Knowledge
MMLU Pro
No call
Only gpt-oss-20b has a MMLU Pro result, 71.6%.
Directional only
Web design
Design Arena: websites
Step 3.7 Flash
Step 3.7 Flash leads, 1196 against 853.
Same board, both measured
Long documents
Listed context window
Step 3.7 Flash
Step 3.7 Flash takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-20b
gpt-oss-20b $0.0001, Step 3.7 Flash $0.0008 per turn.
List prices
At a glance
- Coding index
- gpt-oss-20b not benchmarked, Step 3.7 Flash not benchmarked.
- Widest category
- Agentic work, 38.3 points apart on average over 1 shared benchmark.
- Widest single gap
- Design Arena: websites: gpt-oss-20b 853 against Step 3.7 Flash 1196, 42.9 points apart on a 0 to 100 scale.
- Output price
- gpt-oss-20b $0.15 against Step 3.7 Flash $1.15 per million output tokens, 7.7x apart.
- Context window
- gpt-oss-20b takes 131K tokens, Step 3.7 Flash 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | gpt-oss-20b | Bars | Step 3.7 Flash | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| Web design | 0 | 2 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 11 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 39.6 | Only Step 3.7 Flash measured |
| LiveCodeBench (Vals AI) | 80.4% | Not measured | Only gpt-oss-20b measured |
| LiveCodeBench (Artificial Analysis run) | 77.7% | Not measured | Only gpt-oss-20b measured |
| SciCode | 38.9% | 43.9% | Step 3.7 Flash |
| Terminal-Bench Hard (Artificial Analysis run) | 10.6% | 35.6% | Step 3.7 Flash |
| Terminal-Bench | 3.4% | Not measured | Only gpt-oss-20b measured |
| WeirdML | 40.9% | Not measured | Only gpt-oss-20b measured |
| ALE-Bench | 566.0 | 694.1 | Step 3.7 Flash |
| LMArena Text: coding | 1307 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: software and IT | 1311 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.0 | 19.5 | Step 3.7 Flash |
| Epoch Capabilities Index | 137.7 | Not measured | Only gpt-oss-20b measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 60.2% | 98.5% | Step 3.7 Flash |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 68.9% | Not measured | Only gpt-oss-20b measured |
| GPQA Diamond (Artificial Analysis run) | 68.8% | 80.9% | Step 3.7 Flash |
| Humanity's Last Exam (Artificial Analysis run) | 11.0% | 21.4% | Step 3.7 Flash |
| GPQA Diamond (Epoch AI run) | 60.8% | Not measured | Only gpt-oss-20b measured |
| LMArena Text: hard prompts | 1274 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: expert | 1258 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: hard prompts in English | 1292 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| AIME | 86.0% | Not measured | Only gpt-oss-20b measured |
| MATH 500 (Vals AI) | 94.2% | Not measured | Only gpt-oss-20b measured |
| MGSM (Vals AI) | 89.0% | Not measured | Only gpt-oss-20b measured |
| AA Math Index | 89.3 | Not measured | Only gpt-oss-20b measured |
| AIME 2025 (Artificial Analysis run) | 89.3% | Not measured | Only gpt-oss-20b measured |
| OTIS Mock AIME | 65.3% | Not measured | Only gpt-oss-20b measured |
| LMArena Text: math | 1317 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: mathematical work | 1305 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| MMLU Pro | 71.6% | Not measured | Only gpt-oss-20b measured |
| LegalBench (Vals AI) | 70.8% | Not measured | Only gpt-oss-20b measured |
| CaseLaw (Vals AI) | 43.8% | Not measured | Only gpt-oss-20b measured |
| CorpFin (Vals AI) | 53.1% | Not measured | Only gpt-oss-20b measured |
| TaxEval (Vals AI) | 63.7% | Not measured | Only gpt-oss-20b measured |
| MedQA (Vals AI) | 82.9% | Not measured | Only gpt-oss-20b measured |
| MMLU Pro (Artificial Analysis run) | 74.8% | Not measured | Only gpt-oss-20b measured |
| LMArena Text: science | 1296 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: medicine and healthcare | 1310 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: legal and government | 1280 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: business and finance | 1284 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 853 | 1196 | Step 3.7 Flash |
| Design Arena: UI components | Not measured | 1179 | Only Step 3.7 Flash measured |
| Design Arena: game dev | Not measured | 1158 | Only Step 3.7 Flash measured |
| Design Arena: data viz | 933 | 1172 | Step 3.7 Flash |
| Design Arena: 3D | Not measured | 1129 | Only Step 3.7 Flash measured |
| Design Arena: all code categories | Not measured | 1182 | Only Step 3.7 Flash measured |
| Design Arena: SVG | Not measured | 1085 | Only Step 3.7 Flash measured |
| Design Arena: ASCII art | Not measured | 1152 | Only Step 3.7 Flash measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| IFBench | 65.1% | 67.3% | Step 3.7 Flash |
| Long context reasoning (AA-LCR) | 34.7% | 73.7% | Step 3.7 Flash |
| DTBench | 68.0% | Not measured | Only gpt-oss-20b measured |
| LMCA | 14.5% | Not measured | Only gpt-oss-20b measured |
| LMArena Text | 1288 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: instruction following | 1236 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: creative writing | 1201 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: English | 1303 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: non-English | 1269 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Chinese | 1315 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: German | 1255 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Japanese | 1244 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Korean | 1236 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Spanish | 1267 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Russian | 1278 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Polish | 1252 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: multi-turn | 1268 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: longer queries | 1250 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: writing and language | 1238 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: entertainment and media | 1216 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | gpt-oss-20b | Step 3.7 Flash | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
gpt-oss-20b costs less
Repository review
50K input + 3K output tokens
gpt-oss-20b costs less
Agent loop
200K input + 10K output tokens
gpt-oss-20b costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI gpt-oss-20b | StepFun Step 3.7 Flash |
|---|---|---|
| Maker | OpenAI | StepFun |
| Weights | Open weights | Open weights |
| Released | August 5, 2025 | May 28, 2026 |
| Context window | 131K | 262K |
| Input $/Mtok | $0.03 | $0.20 |
| Output $/Mtok | $0.15 | $1.15 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is gpt-oss-20b better than Step 3.7 Flash for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. gpt-oss-20b has the edge where output tokens cost 7.7x less, and where what matters is SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, gpt-oss-20b or Step 3.7 Flash?
gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. Cost per solved task is known for neither of them.
Which has the bigger context window, gpt-oss-20b or Step 3.7 Flash?
Step 3.7 Flash, with 262K tokens against 131K.
How many benchmarks is the gpt-oss-20b vs Step 3.7 Flash comparison based on?
11 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Step 3.7 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.