Model comparison
DeepSeek-V3 vs GPT-4.1 nano
DeepSeek-V3 is the stronger model overall, scoring 39.2 to 27.7 on the Noometry Index. GPT-4.1 nano costs 2.3× less per token, which makes it the better buy when DeepSeek-V3's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
DeepSeekSummary
- They share 33 benchmarks with published results for both. DeepSeek-V3 scores higher in 8 categories and GPT-4.1 nano in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3 leads 41.9 to 23.8.
- The biggest single-benchmark swing is Aider Polyglot: 55.1% for DeepSeek-V3 and 8.9% for GPT-4.1 nano.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.24 / $0.90 for DeepSeek-V3.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | GPT-4.1 nano | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.2 | 27.7 |
| Released | 2024-12-26 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 164K | 33K |
| Input $ / M tokens | $0.24 | $0.10 |
| Output $ / M tokens | $0.90 | $0.40 |
| Results tracked | 60 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3 leads
DeepSeek-V3: 41.9 (#99), GPT-4.1 nano: 23.8 (#325)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| Aider Polyglot | 55.1% | 8.9% |
| SciCode | 35.8% | 25.9% |
| WeirdML | 36.1% | 19% |
| LMArena Coding | 1368 | 1306 |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, GPT-4.1 nano: 26.3 (#98)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |
| METR Time Horizons | 49.6% | — |
Reasoning DeepSeek-V3 leads
DeepSeek-V3: 20.0 (#226), GPT-4.1 nano: 8.6 (#344)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 33.3% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1365 | 1286 |
| DTBench | 64.8% | 52.5% |
| LMCA | 15.5% | 5.5% |
| Epoch Capabilities Index | 135.95 | 129.62 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 27.2% | — |
| ARC-AGI-1 | — | 0% |
| LiveBench Reasoning | 65.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| BIG-Bench Hard | 87.5% | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math DeepSeek-V3 leads
DeepSeek-V3: 30.4 (#208), GPT-4.1 nano: 25.5 (#246)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 28.9% |
| Omni-MATH | 40.3% | 36.7% |
| LMArena Math | 1373 | 1274 |
| MATH Level 5 | 75.5% | 70% |
| FrontierMath (Feb 2025 set) | 1.7% | 1% |
| LiveBench Math | 73.5% | — |
Knowledge DeepSeek-V3 leads
DeepSeek-V3: 37.5 (#147), GPT-4.1 nano: 21.8 (#268)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 67.6% | 48.9% |
| MMLU-Pro | 72.3% | 55% |
| GPQA (HELM) | 53.8% | 50.7% |
| LMArena Expert | 1352 | 1272 |
| SimpleQA Verified | — | 6% |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multimodal Not comparable
DeepSeek-V3: —, GPT-4.1 nano: 28.6 (#108)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |
Multilingual DeepSeek-V3 leads
DeepSeek-V3: 48.8 (#138), GPT-4.1 nano: 41.8 (#200)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1358 | 1260 |
| LMArena Chinese | 1390 | 1270 |
| LMArena German | 1374 | 1288 |
| LMArena Japanese | 1333 | 1199 |
| LMArena Russian | 1372 | 1261 |
| LMArena French | 1386 | — |
| LMArena Korean | 1321 | — |
| LMArena Spanish | 1358 | — |
Instruction Following DeepSeek-V3 leads
DeepSeek-V3: 73.0 (#125), GPT-4.1 nano: 68.0 (#188)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| IFEval | 83.2% | 84.3% |
| LMArena Instruction Following | 1345 | 1267 |
| LiveBench Instruction Following | 81.5% | — |
Long Context DeepSeek-V3 leads
DeepSeek-V3: 34.0 (#248), GPT-4.1 nano: 23.7 (#291)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| Fiction.LiveBench | 50% | 25% |
| LMArena Longer Query | 1353 | 1283 |
Writing & Preference DeepSeek-V3 leads
DeepSeek-V3: 57.6 (#124), GPT-4.1 nano: 40.7 (#238)
| Benchmark | DeepSeek-V3 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1375 | 1285 |
| LMArena Creative Writing | 1364 | 1260 |
| EQ-Bench Creative Writing | 1472 | 946 |
| WildBench | 83% | 81.2% |
| LMArena Multi-Turn | 1389 | 1277 |
| Short-Story Creative Writing | 77% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than GPT-4.1 nano?
DeepSeek-V3 is the stronger model overall, scoring 39.2 to 27.7 on the Noometry Index. GPT-4.1 nano costs 2.3× less per token, which makes it the better buy when DeepSeek-V3's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3 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-V3 lists at $0.24 and $0.90.
Is DeepSeek-V3 or GPT-4.1 nano better for coding?
DeepSeek-V3 scores higher on coding benchmarks: 41.9 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3 and GPT-4.1 nano share?
33 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and GPT-4.1 nano has 38.