Model comparison
DeepSeek-R1 vs GPT-4.1 nano
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 5.2× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
DeepSeekSummary
- They share 32 benchmarks with published results for both. DeepSeek-R1 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 knowledge, where DeepSeek-R1 leads 44.5 to 21.8.
- The biggest single-benchmark swing is Aider Polyglot: 71.4% for DeepSeek-R1 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 $0.50 / $2.15 for DeepSeek-R1.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-R1 | GPT-4.1 nano | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.3 | 27.9 |
| Released | 2025-01-20 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 64K | 33K |
| Input $ / M tokens | $0.50 | $0.10 |
| Output $ / M tokens | $2.15 | $0.40 |
| Results tracked | 52 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), GPT-4.1 nano: 24.1 (#330)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| Aider Polyglot | 71.4% | 8.9% |
| SciCode | 35.7% | 25.9% |
| WeirdML | 41.6% | 19% |
| LMArena Coding | 1427 | 1306 |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use DeepSeek-R1 leads
DeepSeek-R1: 30.7 (#75), GPT-4.1 nano: 26.5 (#104)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning DeepSeek-R1 leads
DeepSeek-R1: 18.6 (#278), GPT-4.1 nano: 8.5 (#349)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| ARC-AGI-2 | 1.3% | 0% |
| Kagi LLM Benchmark | 69.4% | 33.3% |
| ARC-AGI-1 | 21.2% | 0% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1416 | 1286 |
| Epoch Capabilities Index | 141.29 | 129.62 |
| SimpleBench | 40.8% | — |
| LiveBench Reasoning | 83.2% | — |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 5.5% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), GPT-4.1 nano: 26.9 (#252)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 28.9% |
| Omni-MATH | 42.4% | 36.7% |
| LMArena Math | 1400 | 1274 |
| MATH Level 5 | 96.6% | 70% |
| LiveBench Math | 80.7% | — |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), GPT-4.1 nano: 21.8 (#273)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 76.3% | 48.9% |
| MMLU-Pro | 79.3% | 55% |
| GPQA (HELM) | 66.6% | 50.7% |
| LMArena Expert | 1394 | 1272 |
| SimpleQA Verified | — | 6% |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
Multimodal Not comparable
DeepSeek-R1: —, GPT-4.1 nano: 29.2 (#113)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), GPT-4.1 nano: 41.6 (#205)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1412 | 1260 |
| LMArena Chinese | 1442 | 1270 |
| LMArena German | 1404 | 1288 |
| LMArena Japanese | 1391 | 1198 |
| LMArena Russian | 1423 | 1261 |
| LMArena French | 1417 | — |
| LMArena Korean | 1360 | — |
| LMArena Spanish | 1411 | — |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), GPT-4.1 nano: 67.8 (#193)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| IFEval | 78.4% | 84.3% |
| LMArena Instruction Following | 1382 | 1267 |
| LiveBench Instruction Following | 80.5% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), GPT-4.1 nano: 23.7 (#296)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| Fiction.LiveBench | 75% | 25% |
| LMArena Longer Query | 1391 | 1283 |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), GPT-4.1 nano: 40.5 (#243)
| Benchmark | DeepSeek-R1 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1428 | 1285 |
| LMArena Creative Writing | 1405 | 1260 |
| EQ-Bench Creative Writing | 1500 | 946 |
| WildBench | 82.8% | 81.2% |
| LMArena Multi-Turn | 1405 | 1277 |
| Short-Story Creative Writing | 83% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than GPT-4.1 nano?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 5.2× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 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-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or GPT-4.1 nano better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 24.1 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-R1 and GPT-4.1 nano share?
32 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and GPT-4.1 nano has 38.