- MMLU-Pro 83.7
- AIME25 (no tools) 90.2
- HMMT Feb25 (no tools) 93.7
- GPQA (no tools) 79.2
- LiveCodeBench (v5 2024-07↔2024-12) 81.2
- SciCode (subtask) 42
- HLE (no tools) 18.3
- Terminal Bench (hard subset) 25.8
- Terminal Bench Core 2.0 31
- SWE-Bench (OpenHands) 60.5
- SWE-Bench Multilingual (OpenHands) 45.8
- TauBench V2 Average of Airline 56.25 / Retail 62.83 / Telecom 64.36 61.1
- BrowseComp with Search 31.3
- BIRD Bench 41.8
- IFBench (prompt) 72.6
- Scale AI Multi-Challenge 55.2
- Arena-Hard-V2 73.9
- AA-LCR 58.3
- RULER @ 1M 91.8
- MMLU-ProX (avg over langs) 79.4
- WMT24++ (en→xx) 86.7
Nemotron 3 Super
Nemotron 3 Super ranks first on LiveCodeBench v5.
NVIDIA Released 11 Mar 2026 39
Benchmarks with a score
1
Ranked first, out of five or more models
2
In the top three
NVIDIA Mar 2026 Nemotron 3 Super
Open weights
No Epoch Capabilities Index score yet
- IFBench 72.6% #31 /70
- SciCode 42% #25 /47
- AA-LCR (Artificial Analysis Long Context Reasoning) 58.3% #21 /31
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BullshitBench | 65.5% | #13 of 107 | Official leaderboard | |
| WMT24++ | 86.7% | #2 of 12 | Model card | |
| MMLU-Pro | 83.7% | #43 of 151 | Model card | |
| BullshitBench V2 | 54% | #39 of 122 | Official leaderboard | |
| RULER | 91.8% | #14 of 38 | Model card | |
| Arena-Hard v2.0 | 73.9% | #10 of 24 | Model card | |
| IFBench | 72.6% | #31 of 70 | Model card | |
| LMArena (Elo) | 1,360 | #167 of 333 | Official leaderboard | |
| MMLU-ProX | 79.4% | #10 of 17 | Model card | |
| MultiChallenge | 55.2% | #23 of 36 | Model card | |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 58.3% | #21 of 31 | Model card | |
| Humanity's Last Exam | 18.3% | #105 of 147 | Model card | |
| Extended NYT Connections | 15.4% | #86 of 97 | Official leaderboard | |
| SEA-HELM | 49.3 | #55 of 62 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2025 | 90.2% | #48 of 143 | Model card | |
| HMMT 2025 | 93.7% | #17 of 49 | Model card | |
| GPQA Diamond | 79.2% | #115 of 284 | Model card | |
| CritPt | 3.14% | #78 of 160 | Epoch AI | |
| MathArena (Apex, IMO, USAMO) | 7.81% | #24 of 47 | Official leaderboard | |
| HMMT 2026 | 84.8% | #24 of 31 | Official leaderboard | |
| AIME 2026 | 91.7% | #27 of 31 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v5 | 81.2% | #1 of 44 | Model card | |
| LiveCodeBench v6 | 78.7% | #33 of 76 | Model card | |
| SciCode | 42% | #25 of 47 | Model card | |
| WeirdML | 38% | #90 of 130 | Epoch AI | |
| SWE-bench Verified | 60.5% | #106 of 150 | Model card | |
| Bird-SQL | 41.8% | #11 of 13 | Model card | |
| OpenHands Index | 36.2% | #31 of 33 | Official leaderboard | |
| SWE-bench Multilingual | 45.8% | #67 of 70 | Model card | |
| ALE-Bench | 214 | #118 of 121 | Epoch AI |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Terminal-Bench Hard | 25.8% | #6 of 11 | Model card | |
| PinchBench | 53.9% | #41 of 48 | Official leaderboard | |
| tau2-bench | 61.1% | #59 of 69 | Model card | |
| CivBench | 1,441 | #16 of 18 | Official leaderboard | |
| PinchBench 2.0 | 42.2% | #51 of 57 | Official leaderboard | |
| Terminal-Bench 2.0 | 31% | #57 of 61 | Model card | |
| BrowseComp | 31.3% | #72 of 77 | Model card | |
| Claw-Eval | 44.4% | #23 of 23 | Official leaderboard | |
| Claw-Eval Pass^3 | 5.50% | #23 of 23 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 1 of them isn't in the launch post.
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning 11 Mar 2026
Capabilities
- MMLU-Pro 83.7
- AIME 2025 90.2
- HMMT 2025 93.7
- GPQA Diamond 79.2
- LiveCodeBench v5 81.2
- LiveCodeBench v6 78.7
- SciCode 42
- Humanity's Last Exam 18.3
- Terminal-Bench Hard 25.8
- Terminal-Bench 2.0 31
- SWE-bench Verified 60.5
- SWE-bench Multilingual 45.8
- tau2-bench 61.1
- BrowseComp 31.3
- Bird-SQL 41.8
- IFBench 72.6
- MultiChallenge 55.2
- Arena-Hard v2.0 73.9
- AA-LCR (Artificial Analysis Long Context Reasoning) 58.3
- RULER 91.6
- MMLU-ProX 79.4
- WMT24++ 86.7