Model comparison
DeepSeek V4 Pro vs GPT-4.1 nano
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 5.7× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
DeepSeekSummary
- They share 27 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 9 categories and GPT-4.1 nano in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 8.5.
- The biggest single-benchmark swing is ARC-AGI-1: 90.5% for DeepSeek V4 Pro and 0% for GPT-4.1 nano.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.66 / $1.98 for DeepSeek V4 Pro.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | GPT-4.1 nano | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 54.3 | 27.9 |
| Released | 2026-04-24 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 393K | 33K |
| Input $ / M tokens | $0.66 | $0.10 |
| Output $ / M tokens | $1.98 | $0.40 |
| Results tracked | 48 | 38 |
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), GPT-4.1 nano: 24.1 (#330)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| SciCode | 51% | 25.9% |
| WeirdML | 66.2% | 19% |
| LMArena Coding | 1470 | 1306 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| Aider Polyglot | — | 8.9% |
| LMArena WebDev | 1582 | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use DeepSeek V4 Pro leads
DeepSeek V4 Pro: 32.8 (#58), GPT-4.1 nano: 26.5 (#104)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Berkeley Function Calling Leaderboard | — | 33% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), GPT-4.1 nano: 8.5 (#349)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| ARC-AGI-2 | 61.3% | 0% |
| Kagi LLM Benchmark | 53.5% | 33.3% |
| ARC-AGI-1 | 90.5% | 0% |
| CritPt | 18% | 0% |
| LMArena Hard Prompts | 1461 | 1286 |
| DTBench | 93.9% | 52.5% |
| LMCA | 45.5% | 5.5% |
| Epoch Capabilities Index | 155.31 | 129.62 |
| NYT Connections (extended) | 91.3% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), GPT-4.1 nano: 26.9 (#252)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.6% | 28.9% |
| LMArena Math | 1455 | 1274 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 36.7% |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), GPT-4.1 nano: 21.8 (#273)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 91.7% | 48.9% |
| SimpleQA Verified | 52.9% | 6% |
| LMArena Expert | 1464 | 1272 |
| MMLU-Pro | — | 55% |
| Vectara Hallucination Rate | 8.6% | — |
| GPQA (HELM) | — | 50.7% |
Multimodal Not comparable
DeepSeek V4 Pro: —, GPT-4.1 nano: 29.2 (#113)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), GPT-4.1 nano: 41.6 (#205)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1439 | 1260 |
| LMArena Chinese | 1486 | 1270 |
| LMArena German | 1458 | 1288 |
| LMArena Japanese | 1445 | 1198 |
| LMArena Russian | 1453 | 1261 |
| LMArena French | 1472 | — |
| LMArena Korean | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), GPT-4.1 nano: 67.8 (#193)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Instruction Following | 1448 | 1267 |
| IFEval | — | 84.3% |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), GPT-4.1 nano: 23.7 (#296)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Longer Query | 1458 | 1283 |
| Fiction.LiveBench | — | 25% |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), GPT-4.1 nano: 40.5 (#243)
| Benchmark | DeepSeek V4 Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1451 | 1285 |
| LMArena Creative Writing | 1446 | 1260 |
| EQ-Bench Creative Writing | 1553 | 946 |
| LMArena Multi-Turn | 1467 | 1277 |
| WildBench | — | 81.2% |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than GPT-4.1 nano?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 5.7× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Pro or GPT-4.1 nano?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; DeepSeek V4 Pro lists at $0.66 and $1.98.
Is DeepSeek V4 Pro or GPT-4.1 nano better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4 Pro and GPT-4.1 nano share?
27 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and GPT-4.1 nano has 38.