Data points: 64
The readout for GPT-OSS and Nemotron 3 Super, before the detailed comparison sheet.
Decision read
GPT-OSS
GPT-OSS currently has the stronger profile, with verified wins split 4 to 0.
Evidence depth
64 data points
Includes 0 benchmark rows, 0 audit samples, and 6 provider examples.
Selection signal
Start with GPT-OSS
The charts below split 6 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
Model compare GPT-OSS vs Nemotron 3 Supergpt-oss-vs-nemotron-3-super-120b-a12b | Model A GPT-OSS | Model B Nemotron 3 Super |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 4 wins | 0 wins |
| Where it leads | Cheapest input price, Free providers, Provider coverage, Recent tests |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
No shared professional benchmark scores are available yet.
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-OSS | Nemotron 3 Super |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GPT-OSS | Nemotron 3 Super |
|---|---|---|
35 tests | GPT-OSS speed / latency 347 tok/s / 2670ms input / output No data |
This report only uses LMSpeed data for GPT-OSS and Nemotron 3 Super: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | GPT-OSS | Nemotron 3 Super |
|---|---|---|
| When to choose each model | GPT-OSS GPT-OSS is stronger when you prioritize Cheapest input price, Free providers, Provider coverage, Recent tests. | Nemotron 3 Super Nemotron 3 Super does not clearly lead on the verified metrics here, so check provider-specific pricing before choosing. |
TL;DR: GPT-OSS leads across 64 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from GPT-OSS vs Nemotron 3 Super into nearby model comparisons with enough verified LMSpeed data.
| No data |
| Model metadata | GPT-OSS exposes 131.1K tokens; notable signals: Text input, Text output, Tool calling, Reasoning. | Nemotron 3 Super exposes 1M tokens; notable signals: Text input, Text output, Tool calling, Structured outputs. |
|---|---|---|
| Developer | No data | NVIDIA |
| Context window | 131.1K tokens | 1M tokens |
| Max output | 131.1K tokens | No data |
| Released | Aug 2025 | No data |
| Modalities | Input Text Output Text | Input Text Output Text |
| Features | Text inputText outputTool callingReasoning | Text inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | 120B | 120B / 12B active |
| Tokenizer | GPT | Other |
| Knowledge cutoff | 2024-06-30 | No data |
| OpenRouter ID | openai/gpt-oss-120b:free | nvidia/nemotron-3-super-120b-a12b |
| References | No data | No data |
Nemotron 3 Super
speed / latency
N/A / N/A
input / output
No data
WSocket AI10 tests | GPT-OSS speed / latency 125 tok/s / 2302ms input / output No data | Nemotron 3 Super speed / latency N/A / N/A input / output No data |
|---|
ChooseC API5 tests | GPT-OSS speed / latency 243 tok/s / 2621ms input / output No data | Nemotron 3 Super speed / latency N/A / N/A input / output No data |
|---|
352287 API0 tests | GPT-OSS speed / latency N/A / N/A input / output No data | Nemotron 3 Super speed / latency N/A / N/A input / output No data |
|---|
AI API0 tests | GPT-OSS speed / latency N/A / N/A input / output No data | Nemotron 3 Super speed / latency N/A / N/A input / output No data |
|---|
GPT-OSS tinfoil/gpt-oss-120b speed / latency No data input / output $75.00/M / $75.00/M | Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b:free speed / latency No data input / output $0/M / $0/M |
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
