Model comparison
DeepSeek-V3.2-Exp vs Nemotron 3 Super
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 40.1 on the Noometry Index. Nemotron 3 Super costs 1.7× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 20 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 8 categories and Nemotron 3 Super in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 38.9.
- The biggest single-benchmark swing is NYT Connections (extended): 36.7% for DeepSeek-V3.2-Exp and 15.4% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- Nemotron 3 Super accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.2-Exp | Nemotron 3 Super | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 44.3 | 40.1 |
| Released | 2025-09-29 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.26 | $0.08 |
| Output $ / M tokens | $0.38 | $0.45 |
| Results tracked | 49 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.5 (#65), Nemotron 3 Super: 39.4 (#158)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| SciCode | 38.9% | 36% |
| WeirdML | 39.5% | 38% |
| LMArena Coding | 1454 | 1403 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| ALE-Bench | — | 213.9 |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 32.7 (#59), Nemotron 3 Super: —
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.1 (#208), Nemotron 3 Super: 18.7 (#276)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 36.7% | 15.4% |
| CritPt | 2.9% | 3.1% |
| LMArena Hard Prompts | 1434 | 1386 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| ARC-AGI-1 | 57% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.27 | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), Nemotron 3 Super: 39.6 (#101)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| MathArena Final-Answer Competitions | 57.7% | 60.4% |
| LMArena Math | 1435 | 1380 |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), Nemotron 3 Super: 38.9 (#139)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1436 | 1398 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), Nemotron 3 Super: 48.4 (#144)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1409 | 1355 |
| LMArena Chinese | 1461 | 1432 |
| LMArena French | 1433 | 1405 |
| LMArena German | 1440 | 1341 |
| LMArena Russian | 1424 | 1336 |
| LMArena Spanish | 1440 | 1417 |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1371 | — |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.5 (#93), Nemotron 3 Super: 71.2 (#154)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1413 | 1347 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), Nemotron 3 Super: 41.5 (#139)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1428 | 1362 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.4 (#77), Nemotron 3 Super: 55.9 (#140)
| Benchmark | DeepSeek-V3.2-Exp | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1425 | 1378 |
| LMArena Creative Writing | 1403 | 1317 |
| LMArena Multi-Turn | 1427 | 1369 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Nemotron 3 Super?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 40.1 on the Noometry Index. Nemotron 3 Super costs 1.7× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.2-Exp or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Is DeepSeek-V3.2-Exp or Nemotron 3 Super better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 39.4 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and Nemotron 3 Super share?
20 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Nemotron 3 Super has 21.