Model comparison
DeepSeek V4 Pro vs Nova 2.0 Pro Preview
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 33.4 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeekSummary
- They share 2 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 3 categories and Nova 2.0 Pro Preview in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 22.4.
- The biggest single-benchmark swing is CritPt: 18% for DeepSeek V4 Pro and 0% for Nova 2.0 Pro Preview.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Nova 2.0 Pro Preview | |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 54.3 | 33.4 |
| Released | 2026-04-24 | 2025-12-02 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Nova 2.0 Pro Preview: 40.8 (#133)
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| SciCode | 51% | 42.7% |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| WeirdML | 66.2% | — |
| LMArena Coding | 1470 | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use DeepSeek V4 Pro leads
DeepSeek V4 Pro: 32.8 (#58), Nova 2.0 Pro Preview: 21.9 (#136)
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| APEX-Agents | 47.3% | — |
| GDP.pdf | — | 2% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Nova 2.0 Pro Preview: 22.4 (#194)
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| CritPt | 18% | 0% |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| Chess Puzzles | 47% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
Math Not comparable
DeepSeek V4 Pro: 64.8 (#30), Nova 2.0 Pro Preview: —
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
| LMArena Math | 1455 | — |
Knowledge Not comparable
DeepSeek V4 Pro: 59.5 (#31), Nova 2.0 Pro Preview: —
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), Nova 2.0 Pro Preview: —
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |
Instruction Following Not comparable
DeepSeek V4 Pro: 76.1 (#47), Nova 2.0 Pro Preview: —
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Nova 2.0 Pro Preview: —
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference Not comparable
DeepSeek V4 Pro: 65.5 (#46), Nova 2.0 Pro Preview: —
| Benchmark | DeepSeek V4 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Nova 2.0 Pro Preview?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 33.4 on the Noometry Index.
Is DeepSeek V4 Pro or Nova 2.0 Pro Preview better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 40.8 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Nova 2.0 Pro Preview share?
2 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Nova 2.0 Pro Preview has 3.