Model comparison
GPT-OSS 20B vs Nemotron 3 Ultra
Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: GPT-OSS 20B unranked; Nemotron 3 Ultra #24
BenchAlign evidence: GPT-OSS 20B supported; Nemotron 3 Ultra not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-OSS 20B and Nemotron 3 Ultra share 17 comparable benchmark results. 0 of 8 categories are comparable. 2 results are unique to GPT-OSS 20B; 22 to Nemotron 3 Ultra.
Updated July 16, 2026- Shared results
- 17
- GPT-OSS 20B only
- 2
- Nemotron 3 Ultra only
- 22
- Comparable categories
- 0 / 8
Benchmark data for GPT-OSS 20B and Nemotron 3 Ultra is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Nemotron 3 Ultra has the larger context window at 1M, compared with 128K for GPT-OSS 20B.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | GPT-OSS 20B | Δ | Nemotron 3 Ultra |
|---|---|---|---|
| Agentic | GPT-OSS 20BNot measured | MarginNo overlap | Nemotron 3 Ultra51.3 |
| Coding | GPT-OSS 20BNot measured | MarginNo overlap | Nemotron 3 Ultra58.3 |
| Reasoning | GPT-OSS 20BNot measured | MarginNo overlap | Nemotron 3 Ultra61.9 |
| Knowledge | GPT-OSS 20BNot measured | MarginNo overlap | Nemotron 3 Ultra54.2 |
| Multilingual | GPT-OSS 20BNot measured | MarginNo overlap | Nemotron 3 Ultra83.0 |
| Inst. Following | GPT-OSS 20BNot measured | MarginNo overlap | Nemotron 3 Ultra81.7 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-OSS 20B | Nemotron 3 Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-OSS 20B$0 input / $0 output | Nemotron 3 Ultra$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | GPT-OSS 20B313 tok/s | Nemotron 3 UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-OSS 20B0.65 s | Nemotron 3 UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-OSS 20B128K | Nemotron 3 Ultra1M | Nemotron 3 Ultra lists the larger context window. |
Benchmark Deep Dive
Agentic13 benchmarks
| Benchmark | GPT-OSS 20B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| AA Agentic IndexSource | 3.1% | 27.4% | Nemotron 3 Ultra leads |
| APEX-Agents-AASource | 0.7% | — | Not comparable |
| τ²-bench resultsSource | 60.2% | 83.3% | Nemotron 3 Ultra leads |
| GDPval-AASource | 3.0% | 33.2% | Nemotron 3 Ultra leads |
| GDPval-AASource | 559 | 1164 | Nemotron 3 Ultra leads |
| Terminal-Bench 2.0Source | — | 56.4% | Not comparable |
| PinchBenchSource | — | 90.0% | Not comparable |
| BrowseCompSource | — | 44.4% | Not comparable |
| τ³-bench resultsSource | — | 70.9% | Not comparable |
| HLE w/ toolsSource | — | 37.4% | Not comparable |
| AA BriefcaseSource | — | 870 | Not comparable |
| AA EnterpriseOps-GymSource | — | 28.9% | Not comparable |
| AA Harvey LABSource | — | 3.3% | Not comparable |
Coding9 benchmarks
| Benchmark | GPT-OSS 20B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| React Native EvalsSource | 71% | — | Not comparable |
| AA Coding IndexSource | 20.7% | 49.3% | Nemotron 3 Ultra leads |
| Terminal-Bench HardSource | 10.6% | 36.4% | Nemotron 3 Ultra leads |
| AA-SciCodeSource | 34.4% | 39.9% | Nemotron 3 Ultra leads |
| SWE-bench VerifiedSource | — | 71.9% | Not comparable |
| SWE MultilingualSource | — | 67.7% | Not comparable |
| LiveCodeBench v6Source | — | 89.0% | Not comparable |
| SciCodeSource | — | 44.6% | Not comparable |
| Terminal-Bench 2.0Source | — | 56.4% | Not comparable |
Reasoning3 benchmarks
Knowledge12 benchmarks
| Benchmark | GPT-OSS 20B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 14.9% | 37.8% | Nemotron 3 Ultra leads |
| AA-GPQA DiamondSource | 68.8% | 86.7% | Nemotron 3 Ultra leads |
| AA-HLESource | 9.8% | 26.6% | Nemotron 3 Ultra leads |
| AA-Omniscience IndexSource | -63.9% | -0.8% | Nemotron 3 Ultra leads |
| AA-Omniscience AccuracySource | 15.5% | 21.6% | Nemotron 3 Ultra leads |
| AA-Omniscience Hallucination RateSource | 94.1% | 28.5% | Nemotron 3 Ultra leads |
| GPQASource | — | 87% | Not comparable |
| GPQA-DSource | — | 87.0% | Not comparable |
| HLESource | — | 26.7% | Not comparable |
| HLE w/o toolsSource | — | 26.7% | Not comparable |
| MMLU-ProSource | — | 86.8% | Not comparable |
| AA Openness IndexSource | — | 83.3% | Not comparable |
Multilingual1 benchmarks
| Benchmark | GPT-OSS 20B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| MMLU-ProXSource | — | 83% | Not comparable |
Multimodal1 benchmarks
| Benchmark | GPT-OSS 20B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 887 | 1132 | Nemotron 3 Ultra leads |
Frequently Asked Questions (3)
Can I compare GPT-OSS 20B and Nemotron 3 Ultra on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for GPT-OSS 20B and Nemotron 3 Ultra today?
GPT-OSS 20B: $0.00 input / $0.00 output per 1M tokens Nemotron 3 Ultra: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.