Nemotron 3 Super 120B A12B
- Input
- $0.30/M tok
- Output
- $0.90/M tok
- Blended
- $0.45/M tok · 3:1
- Speed
- 164tok/s
- Context
- 1Mtokens
- Cost per task
- ~$0.38/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Nemotron 3 Super 120B A12B (Reasoning). Price = AA median host price.
Rankings
Coding
Verified#110 / 137rank by quality29.4±8.1quality / 1002/7 benchmarks measuredWriting & chat
Verified#76 / 162rank by quality49.1±9.5quality / 1001/5 benchmarks measuredHard reasoning
Verified#111 / 218rank by quality42.6±3.7quality / 1003/4 benchmarks measuredAgents
Verified#107 / 187rank by quality27.7±4.3quality / 1004/7 benchmarks measured
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.
- Hardware
- 2× B200 180GB
- FP8 weights
- Throughput
- ~12,551 tok/s
- many requests batched
- Price
- $0.11–0.96 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Max 128GB (int4, ~72 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (120B params, 12B active per token) + 40% KV-cache headroom ≈ 168 GB
- 2× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~12,551 output tok/s aggregate at batch 359 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~177,188 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#17 of 21 (estimated)~68.6%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #16Nemotron 3 Ultra70.7%
- ~#17Nemotron 3 Super 120B A12BEstimated68.6%
- #17Intern-S2-Preview (35B-A3B)64.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#23 of 24 (estimated)~47.3%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #22Muse Glimmer51.2%
- ~#23Nemotron 3 Super 120B A12BEstimated47.3%
- #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#41 of 46 (estimated)~41.5%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #40Qwen3.8 27B42.2%
- ~#41Nemotron 3 Super 120B A12BEstimated41.5%
- #41Laguna S 2.140.4%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#63 of 1010.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #63Mistral Small 40.0%
- #63Nemotron 3 Super 120B A12B0.0%
- #63Nemotron 3.5 Bolt 74B-A9B0.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#17 of 28 (estimated)~58.7%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #16Claude Haiku 4.561.5%
- ~#17Nemotron 3 Super 120B A12BEstimated58.7%
- #17GLM-5.3 NVFP453.5%
No published score — estimated from related benchmarks
SciCodeVerified
#95 of 11836.2%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #94LongCat 2.036.3%
- #95Nemotron 3 Super 120B A12B36.2%
- #95Qwen3 Coder Next36.2%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~28.7
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25Nemotron 3 Super 120B A12BEstimated28.7
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#31 of 13971.5%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #30Gemma 4 26B A4B72.4%
- #31Nemotron 3 Super 120B A12B71.5%
- #31Nemotron 3.5 Super VL NVFP471.5%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~#3 of 5 (estimated)~83.5%
- #1Gemini 3.1 Pro92.6%
- #2Gemma 4 31B88.4%
- ~#3Nemotron 3 Super 120B A12BEstimated83.5%
- #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#44 of 57 (estimated)~1375 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #43Qwen3 Next 80B A3B Instruct1386
- ~#44Nemotron 3 Super 120B A12BEstimated1375
- #44GLM-4.6VFew votes1361
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#44 of 57 (estimated)~1393 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #43Qwen3 Next 80B A3B Instruct1399
- ~#44Nemotron 3 Super 120B A12BEstimated1393
- #44GLM-4.6VFew votes1378
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#21 of 26 (estimated)~1521 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #20DeepSeek V4.1 Flash1540
- ~#21Nemotron 3 Super 120B A12BEstimated1521
- #21Gemini 3.1 Pro1491
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#79 of 19280.0%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #78G9v3-39A5B80.5%
- #79Nemotron 3 Super 120B A12B80.0%
- #80EXAONE 4.5 33B79.4%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#79 of 19820.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #78Step 3.7 Flash21.4%
- #79Nemotron 3 Super 120B A12B20.8%
- #80o320.1%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~77.0%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Nemotron 3 Super 120B A12BEstimated77.0%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#43 of 11967.8%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #42Apriel-v1.6-15B-Thinker69.3%
- #43Nemotron 3 Super 120B A12B67.8%
- #44gpt-oss-120b65.8%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~60.8%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Nemotron 3 Super 120B A12BEstimated60.8%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~57.5%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Nemotron 3 Super 120B A12BEstimated57.5%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#72 of 91477 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #71Granite 4.2 8B478
- #72Nemotron 3 Super 120B A12B477
- #73Mercury 2.5462
artificialanalysis.ai · 2026-09-24