Model comparison
GPT-OSS 120B vs Nemotron 3 Nano Omni 30B A3B
Head-to-head evidence from 14 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-OSS 120B #122 (Supported); Nemotron 3 Nano Omni 30B A3B #159 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-OSS 120B and Nemotron 3 Nano Omni 30B A3B share 14 comparable benchmark results. 0 of 8 categories are comparable. 14 results are unique to GPT-OSS 120B; 15 to Nemotron 3 Nano Omni 30B A3B.
Updated July 27, 2026- Shared results
- 14
- GPT-OSS 120B only
- 14
- Nemotron 3 Nano Omni 30B A3B only
- 15
- Comparable categories
- 0 / 8
Benchmark data for GPT-OSS 120B and Nemotron 3 Nano Omni 30B A3B is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 5 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 Nano Omni 30B A3B has the larger context window at 256K, compared with 128K for GPT-OSS 120B.
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 120B | Δ | Nemotron 3 Nano Omni 30B A3B |
|---|---|---|---|
| Coding | GPT-OSS 120BNot measured | MarginNo overlap | Nemotron 3 Nano Omni 30B A3B32.0 |
| Knowledge | GPT-OSS 120BNot measured | MarginNo overlap | Nemotron 3 Nano Omni 30B A3B76.3 |
| Multimodal | GPT-OSS 120BNot measured | MarginNo overlap | Nemotron 3 Nano Omni 30B A3B76.3 |
| Inst. Following | GPT-OSS 120BNot measured | MarginNo overlap | Nemotron 3 Nano Omni 30B A3B74.2 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-OSS 120B | Nemotron 3 Nano Omni 30B A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-OSS 120B$0 input / $0 output | Nemotron 3 Nano Omni 30B A3B$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | GPT-OSS 120B262 tok/s | Nemotron 3 Nano Omni 30B A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-OSS 120B0.79 s | Nemotron 3 Nano Omni 30B A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-OSS 120B128K | Nemotron 3 Nano Omni 30B A3B256K | Nemotron 3 Nano Omni 30B A3B lists the larger context window. |
Benchmark Deep Dive
Agentic11 benchmarks
| Benchmark | GPT-OSS 120B | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| AA Agentic IndexSource | 13.2% | — | Not comparable |
| APEX-Agents-AASource | 3.1% | — | Not comparable |
| τ²-bench resultsSource | 65.8% | 45.3% | GPT-OSS 120B leads |
| GDPval-AASource | 15.1% | 0.0% | GPT-OSS 120B leads |
| GDPval-AASource | 802 | 465 | GPT-OSS 120B leads |
| Gert LabsSource | 29.61% | — | Not comparable |
| AA ITBenchSource | 5.6% | — | Not comparable |
| AA EnterpriseOps-GymSource | 25.5% | — | Not comparable |
| AA Harvey LABSource | 13.9% | — | Not comparable |
| terminalBenchHardSource | 23.5% | — | Not comparable |
| OSWorldSource | — | 47.4% | Not comparable |
Coding5 benchmarks
Reasoning2 benchmarks
Knowledge11 benchmarks
| Benchmark | GPT-OSS 120B | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 23.8% | 14.9% | GPT-OSS 120B leads |
| AA-GPQA DiamondSource | 78.2% | 46.9% | GPT-OSS 120B leads |
| AA-HLESource | 18.5% | 5.3% | GPT-OSS 120B leads |
| AA-Omniscience IndexSource | -50.0% | -56.0% | GPT-OSS 120B leads |
| AA-Omniscience AccuracySource | 21.5% | 14.8% | GPT-OSS 120B leads |
| AA-Omniscience Hallucination RateSource | 91.2% | 83.1% | Nemotron 3 Nano Omni 30B A3B leads |
| AA Openness IndexSource | 38.9% | — | Not comparable |
| AA MMLU-ProSource | 80.8% | — | Not comparable |
| MMLU-ProSource | — | 77.3% | Not comparable |
| GPQASource | — | 72.2% | Not comparable |
| GPQA-DSource | — | 72.2% | Not comparable |
Math2 benchmarks
Multilingual1 benchmarks
| Benchmark | GPT-OSS 120B | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| AA Global-MMLU-LiteSource | 82.8% | — | Not comparable |
Multimodal9 benchmarks
| Benchmark | GPT-OSS 120B | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 993 | — | Not comparable |
| MMMUSource | — | 70.8% | Not comparable |
| MMLongBench-DocSource | — | 57.5% | Not comparable |
| CharXivSource | — | 76.3% | Not comparable |
| ScreenSpot ProSource | — | 57.8% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 72.2% | Not comparable |
| AI2D_TESTSource | — | 88.5% | Not comparable |
| RefCOCO (avg)Source | — | 90.5% | Not comparable |
| AA-MMMU-ProSource | — | 53.2% | Not comparable |
Frequently Asked Questions (3)
Can I compare GPT-OSS 120B and Nemotron 3 Nano Omni 30B A3B 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 120B and Nemotron 3 Nano Omni 30B A3B today?
GPT-OSS 120B: $0.00 input / $0.00 output per 1M tokens Nemotron 3 Nano Omni 30B A3B: $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
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
One email each week. Unsubscribe anytime.