Model comparison
gpt-oss-20b vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 32.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFunSummary
- They share 12 benchmarks with published results for both. gpt-oss-20b scores higher in 1 category and Step 2 16k Exp 202412 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 2 16k Exp 202412 leads 52.3 to 35.5.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 32.5 | 39.2 |
| Released | 2025-08-05 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
gpt-oss-20b: 37.6 (#192), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1306 | 1316 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Step 2 16k Exp 202412: —
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Step 2 16k Exp 202412 leads
gpt-oss-20b: 19.3 (#261), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1299 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1317 | 1304 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge Too close to call
gpt-oss-20b: 34.6 (#195), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1258 | 1279 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Step 2 16k Exp 202412 leads
gpt-oss-20b: 42.2 (#197), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1268 | 1290 |
| LMArena Chinese | 1314 | 1331 |
| LMArena Russian | 1278 | 1324 |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Step 2 16k Exp 202412 leads
gpt-oss-20b: 61.8 (#240), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1287 |
| IFEval | 73.2% | — |
Long Context Step 2 16k Exp 202412 leads
gpt-oss-20b: 37.9 (#209), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1250 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
gpt-oss-20b: 35.5 (#265), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | gpt-oss-20b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1287 | 1321 |
| LMArena Creative Writing | 1201 | 1328 |
| LMArena Multi-Turn | 1268 | 1292 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 32.5 on the Noometry Index.
Is gpt-oss-20b or Step 2 16k Exp 202412 better for coding?
They score almost the same on coding (37.6 vs 38.5); test both on your own repository before choosing.
How many benchmarks do gpt-oss-20b and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Step 2 16k Exp 202412 has 12.