Model comparison
gpt-oss-120b vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 36.0 on the Noometry Index. gpt-oss-120b costs 2.5× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
NVIDIASummary
- They share 19 benchmarks with published results for both. gpt-oss-120b scores higher in 3 categories and Nemotron 3 Super in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 37.6.
- The biggest single-benchmark swing is WeirdML: 48.2% for gpt-oss-120b and 38% for Nemotron 3 Super.
- gpt-oss-120b is cheaper at $0.037 / $0.17 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-120b | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 36.0 | 39.6 |
| Released | 2025-08-05 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 41K | 131K |
| Input $ / M tokens | $0.037 | $0.08 |
| Output $ / M tokens | $0.17 | $0.45 |
| Results tracked | 48 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
gpt-oss-120b: 33.2 (#251), Nemotron 3 Super: 38.9 (#153)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| SciCode | 36% | 36% |
| WeirdML | 48.2% | 38% |
| LMArena Coding | 1380 | 1403 |
| ALE-Bench | 575.62 | 213.9 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.1 (#145), Nemotron 3 Super: —
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 19.5 (#236), Nemotron 3 Super: 17.9 (#274)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| CritPt | 1.1% | 3.1% |
| LMArena Hard Prompts | 1364 | 1386 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| NYT Connections (extended) | — | 15.4% |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.94 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), Nemotron 3 Super: 37.6 (#95)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1388 | 1381 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.3 (#89), Nemotron 3 Super: 38.2 (#136)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1356 | 1397 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual Too close to call
gpt-oss-120b: 48.2 (#142), Nemotron 3 Super: 48.6 (#139)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1350 | 1356 |
| LMArena Chinese | 1384 | 1430 |
| LMArena French | 1370 | 1404 |
| LMArena German | 1355 | 1341 |
| LMArena Russian | 1343 | 1336 |
| LMArena Spanish | 1388 | 1417 |
| LMArena Japanese | 1332 | — |
| LMArena Korean | 1283 | — |
Instruction Following Nemotron 3 Super leads
gpt-oss-120b: 69.5 (#168), Nemotron 3 Super: 71.4 (#149)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1318 | 1347 |
| IFEval | 83.6% | — |
Long Context Nemotron 3 Super leads
gpt-oss-120b: 31.4 (#273), Nemotron 3 Super: 41.5 (#134)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1319 | 1362 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Nemotron 3 Super leads
gpt-oss-120b: 46.7 (#213), Nemotron 3 Super: 56.1 (#135)
| Benchmark | gpt-oss-120b | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1366 | 1378 |
| LMArena Creative Writing | 1274 | 1317 |
| LMArena Multi-Turn | 1340 | 1369 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 36.0 on the Noometry Index. gpt-oss-120b costs 2.5× 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-120b or Nemotron 3 Super?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is gpt-oss-120b or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 33.2 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-120b and Nemotron 3 Super share?
19 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Nemotron 3 Super has 21.