Model comparison
Amazon Nova Pro vs DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 31.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeekSummary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and DeepSeek V4.1 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 28.5.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 300K.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 31.0 | 52.8 |
| Released | 2024-12-03 | 2026-09-09 |
| Weights | Proprietary | Open |
| Context window | 300K | 1M |
| Max output | 10K | 393K |
| Input $ / M tokens | $0.80 | $0.15 |
| Output $ / M tokens | $3.20 | $0.60 |
| Results tracked | 38 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
Amazon Nova Pro: 35.1 (#229), DeepSeek V4.1 Flash: 52.9 (#32)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Coding | 1270 | 1506 |
| LMArena WebDev | — | 1619 |
| SciCode | — | 51.9% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,092 |
Agentic & Tool Use DeepSeek V4.1 Flash leads
Amazon Nova Pro: 16.7 (#147), DeepSeek V4.1 Flash: 31.2 (#69)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | — | 39.5% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| GDP.pdf | — | 19.8% |
Reasoning DeepSeek V4.1 Flash leads
Amazon Nova Pro: 20.0 (#243), DeepSeek V4.1 Flash: 50.2 (#36)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1483 |
| Epoch Capabilities Index | 123.8 | 154.9 |
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 14.3% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 43% |
| DTBench | — | 89.9% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| LiveBench | 43.5% | — |
Math DeepSeek V4.1 Flash leads
Amazon Nova Pro: 28.5 (#243), DeepSeek V4.1 Flash: 66.7 (#25)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Math | 1252 | 1477 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 26.8% |
| OTIS Mock AIME 2024-2025 | — | 98.3% |
| ProofBench | — | 54% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge DeepSeek V4.1 Flash leads
Amazon Nova Pro: 27.4 (#250), DeepSeek V4.1 Flash: 57.9 (#38)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Expert | 1211 | 1506 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal DeepSeek V4.1 Flash leads
Amazon Nova Pro: 25.0 (#126), DeepSeek V4.1 Flash: 39.1 (#61)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | 980 | 1277 |
| Furniture Assembly | — | 34.2% |
Multilingual DeepSeek V4.1 Flash leads
Amazon Nova Pro: 39.7 (#223), DeepSeek V4.1 Flash: 55.0 (#35)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1234 | 1448 |
| LMArena Chinese | 1244 | 1497 |
| LMArena French | 1271 | 1452 |
| LMArena German | 1243 | 1484 |
| LMArena Japanese | 1200 | 1412 |
| LMArena Korean | 1203 | 1452 |
| LMArena Russian | 1240 | 1471 |
| LMArena Spanish | 1182 | 1459 |
Instruction Following DeepSeek V4.1 Flash leads
Amazon Nova Pro: 64.9 (#226), DeepSeek V4.1 Flash: 77.3 (#26)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1235 | 1474 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context DeepSeek V4.1 Flash leads
Amazon Nova Pro: 38.1 (#205), DeepSeek V4.1 Flash: 45.2 (#47)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1255 | 1475 |
Writing & Preference DeepSeek V4.1 Flash leads
Amazon Nova Pro: 43.9 (#226), DeepSeek V4.1 Flash: 65.4 (#48)
| Benchmark | Amazon Nova Pro | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1259 | 1462 |
| LMArena Creative Writing | 1212 | 1435 |
| LMArena Multi-Turn | 1246 | 1457 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1540 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or DeepSeek V4.1 Flash better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 300K.
How many benchmarks do Amazon Nova Pro and DeepSeek V4.1 Flash share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and DeepSeek V4.1 Flash has 37.