Model comparison
DeepSeek V4 Pro vs Nova Premier 1.0
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 38.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek V4 Pro scores higher in 5 categories and Nova Premier 1.0 in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 23.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.5% for DeepSeek V4 Pro and 44.8% for Nova Premier 1.0.
- DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Nova Premier 1.0 | |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 54.3 | 38.3 |
| Released | 2026-04-24 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 393K | 10K |
| Input $ / M tokens | $0.66 | $2.50 |
| Output $ / M tokens | $1.98 | $12.50 |
| Results tracked | 48 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek V4 Pro: 52.4 (#34), Nova Premier 1.0: —
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| LMArena Coding | 1470 | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Nova Premier 1.0: —
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Nova Premier 1.0: 23.0 (#185)
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 53.5% | 44.8% |
| ARC-AGI-2 | 61.3% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| 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 DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Nova Premier 1.0: 33.8 (#199)
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| 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% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1455 | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Nova Premier 1.0: 35.8 (#180)
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| MMLU-Pro | — | 72.6% |
| Vectara Hallucination Rate | 8.6% | — |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1464 | — |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), Nova Premier 1.0: —
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| 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 DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Nova Premier 1.0: 66.8 (#204)
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Nova Premier 1.0: —
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Nova Premier 1.0: 51.0 (#178)
| Benchmark | DeepSeek V4 Pro | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| WildBench | — | 78.8% |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Nova Premier 1.0?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 38.3 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or Nova Premier 1.0?
DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do DeepSeek V4 Pro and Nova Premier 1.0 share?
1 benchmark has published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Nova Premier 1.0 has 6.