Model comparison
gpt-oss-20b vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 4.8× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
NVIDIASummary
- They share 18 benchmarks with published results for both. gpt-oss-20b scores higher in 1 category and Nemotron 3 Super in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Super leads 55.9 to 35.5.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
- Nemotron 3 Super accepts more context: 262K tokens versus 131K.
Side by side
| gpt-oss-20b | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 32.5 | 40.1 |
| Released | 2025-08-05 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.018 | $0.08 |
| Output $ / M tokens | $0.09 | $0.45 |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
gpt-oss-20b: 37.6 (#192), Nemotron 3 Super: 39.4 (#158)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| SciCode | 34.4% | 36% |
| WeirdML | 40.9% | 38% |
| LMArena Coding | 1306 | 1403 |
| ALE-Bench | 566.05 | 213.9 |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Nemotron 3 Super: —
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Too close to call
gpt-oss-20b: 19.3 (#261), Nemotron 3 Super: 18.7 (#276)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| CritPt | 1.4% | 3.1% |
| LMArena Hard Prompts | 1274 | 1386 |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 15.4% |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math Too close to call
gpt-oss-20b: 39.4 (#103), Nemotron 3 Super: 39.6 (#101)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1317 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge Nemotron 3 Super leads
gpt-oss-20b: 34.6 (#195), Nemotron 3 Super: 38.9 (#139)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1258 | 1398 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Nemotron 3 Super leads
gpt-oss-20b: 42.2 (#197), Nemotron 3 Super: 48.4 (#144)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1268 | 1355 |
| LMArena Chinese | 1314 | 1432 |
| LMArena German | 1255 | 1341 |
| LMArena Russian | 1278 | 1336 |
| LMArena Spanish | 1267 | 1417 |
| LMArena French | — | 1405 |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
Instruction Following Nemotron 3 Super leads
gpt-oss-20b: 61.8 (#240), Nemotron 3 Super: 71.2 (#154)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1236 | 1347 |
| IFEval | 73.2% | — |
Long Context Nemotron 3 Super leads
gpt-oss-20b: 37.9 (#209), Nemotron 3 Super: 41.5 (#139)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1250 | 1362 |
Writing & Preference Nemotron 3 Super leads
gpt-oss-20b: 35.5 (#265), Nemotron 3 Super: 55.9 (#140)
| Benchmark | gpt-oss-20b | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1287 | 1378 |
| LMArena Creative Writing | 1201 | 1317 |
| LMArena Multi-Turn | 1268 | 1369 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 4.8× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Nemotron 3 Super?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is gpt-oss-20b or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-20b and Nemotron 3 Super share?
18 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Nemotron 3 Super has 21.