NVIDIA-Nemotron-3-Super-120B-A12B-FP8: benchmark scores, price and ranking
NVIDIA-Nemotron-3-Super-120B-A12B-FP8 from nvidia ranks #183 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.5), based on 1 benchmark results captured up to 2026-10-14.
- Organisation
- nvidia
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #183 of 743 (score 50.5)
Across the 1 benchmark where at least ten models are scored, NVIDIA-Nemotron-3-Super-120B-A12B-FP8 is in the top 10% on 0 and in the top half on 1.
NVIDIA-Nemotron-3-Super-120B-A12B-FP8 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 77.3% | #118 of 277 | HuggingFace GPQA Diamond leaderboard | 2026-10-14 |
About NVIDIA-Nemotron-3-Super-120B-A12B-FP8
NVIDIA-Nemotron-3-Super-120B-A12B-FP8 is an open-weight model that can run on your own hardware from nvidia. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where NVIDIA-Nemotron-3-Super-120B-A12B-FP8 stands
On our aggregate score, NVIDIA-Nemotron-3-Super-120B-A12B-FP8 is #183 of 743 ranked models, in the top quarter. Its score is 50.5; the scale is centred on 50, so it sits 0.5 points above the typical model. That beats 75% of the ranked field. Among the 9 ranked nvidia models it is #6. The next one up is NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 at 51.5. The next one down is Nemotron-Cascade-2-30B-A3B at 50.4.
NVIDIA-Nemotron-3-Super-120B-A12B-FP8, benchmark by benchmark
GPQA Diamond puts NVIDIA-Nemotron-3-Super-120B-A12B-FP8 at 77.3%, #118 of 277. That beats 57% of the models tested, but 19.1 points short of gemini-4-argon-high (96.4%). The results either side are claude-opus-4-1-20250805_16K (77.3%) and o3-mini (high) (77.0%). It covers expert-level science questions. The board median is 72.2%, so NVIDIA-Nemotron-3-Super-120B-A12B-FP8 is 5.1 points above it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-14.
Reading these numbers
The 1 score on this page comes from 1 source: HuggingFace GPQA Diamond leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #180 chatgpt-4o-01-29-2025 (50.6)
- #181 Claude Sonnet 4.5 (59k thinking) (50.6)
- #182 Gemini 3 Pro (50.6)
- #184 Claude 3.7 Sonnet w/ Review Heavy (50.5)
- #185 GPT-5-codex (high) (50.5)
- #186 DeepSeek Chat V3 (prev) (50.5)
More from nvidia
- NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 (#41, 53.1)
- NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (#44, 53.0)
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (#84, 52.0)
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 (#115, 51.5)
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 (#118, 51.5)
- Nemotron-Cascade-2-30B-A3B (#195, 50.4)
Compare it on the live leaderboard → · How the aggregate score works