Model comparison
Amazon Nova Experimental Chat 10 09 vs DeepSeek V4 Pro
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 41.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. Amazon Nova Experimental Chat 10 09 scores higher in 0 categories and DeepSeek V4 Pro in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 27.3.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 41.9 | 54.3 |
| Released | — | 2026-04-24 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1.98 |
| Results tracked | 9 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
Amazon Nova Experimental Chat 10 09: 40.2 (#145), DeepSeek V4 Pro: 52.4 (#34)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Coding | 1370 | 1470 |
| SWE-bench Verified | — | 77.6% |
| FrontierCode | — | 28.6% |
| LMArena WebDev | — | 1582 |
| SciCode | — | 51% |
| WeirdML | — | 66.2% |
| ALE-Bench | — | 1,403 |
Agentic & Tool Use Not comparable
Amazon Nova Experimental Chat 10 09: —, DeepSeek V4 Pro: 32.8 (#58)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| APEX-Agents | — | 47.3% |
| Vending-Bench 2 | — | 3,285 |
Reasoning DeepSeek V4 Pro leads
Amazon Nova Experimental Chat 10 09: 27.3 (#120), DeepSeek V4 Pro: 56.5 (#24)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1461 |
| ARC-AGI-2 | — | 61.3% |
| Kagi LLM Benchmark | — | 53.5% |
| NYT Connections (extended) | — | 91.3% |
| ARC-AGI-1 | — | 90.5% |
| CritPt | — | 18% |
| Chess Puzzles | — | 47% |
| 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
Amazon Nova Experimental Chat 10 09: —, DeepSeek V4 Pro: 64.8 (#30)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| 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
Amazon Nova Experimental Chat 10 09: —, DeepSeek V4 Pro: 59.5 (#31)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| GPQA Diamond | — | 91.7% |
| SimpleQA Verified | — | 52.9% |
| Vectara Hallucination Rate | — | 8.6% |
| LMArena Expert | — | 1464 |
Multilingual DeepSeek V4 Pro leads
Amazon Nova Experimental Chat 10 09: 47.3 (#150), DeepSeek V4 Pro: 54.4 (#45)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Non-English | 1340 | 1439 |
| LMArena Chinese | 1341 | 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
Amazon Nova Experimental Chat 10 09: 69.4 (#172), DeepSeek V4 Pro: 76.1 (#47)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Instruction Following | 1315 | 1448 |
Long Context DeepSeek V4 Pro leads
Amazon Nova Experimental Chat 10 09: 40.5 (#152), DeepSeek V4 Pro: 45.0 (#51)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Longer Query | 1333 | 1458 |
| CL-bench Life | — | 13.5% |
Writing & Preference DeepSeek V4 Pro leads
Amazon Nova Experimental Chat 10 09: 54.7 (#149), DeepSeek V4 Pro: 65.5 (#46)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Text | 1364 | 1451 |
| LMArena Creative Writing | 1307 | 1446 |
| LMArena Multi-Turn | 1355 | 1467 |
| EQ-Bench Creative Writing | — | 1553 |
| EQ-Bench 4 | — | 1166 |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 09 better than DeepSeek V4 Pro?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 41.9 on the Noometry Index.
Is Amazon Nova Experimental Chat 10 09 or DeepSeek V4 Pro better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 40.2 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 10 09 and DeepSeek V4 Pro share?
9 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 09 has 9 scored results on Noometry and DeepSeek V4 Pro has 48.