Model comparison
DeepSeek-R1-Distill-Qwen-14B vs GPT-4.1 nano
DeepSeek-R1-Distill-Qwen-14B is the stronger model overall, scoring 32.7 to 27.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeekSummary
- They share 4 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-14B scores higher in 4 categories and GPT-4.1 nano in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-R1-Distill-Qwen-14B leads 36.9 to 24.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 50.6% for DeepSeek-R1-Distill-Qwen-14B and 28.9% for GPT-4.1 nano.
- DeepSeek-R1-Distill-Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 32.7 | 27.9 |
| Released | 2025-01-20 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 7 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Qwen-14B leads
DeepSeek-R1-Distill-Qwen-14B: 36.9 (#200), GPT-4.1 nano: 24.1 (#330)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| Aider Polyglot | — | 8.9% |
| SciCode | — | 25.9% |
| WeirdML | — | 19% |
| BigCodeBench Instruct | 38.1% | — |
| LMArena Coding | — | 1306 |
| BigCodeBench Complete | 48.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-R1-Distill-Qwen-14B: —, GPT-4.1 nano: 26.5 (#104)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |
Reasoning DeepSeek-R1-Distill-Qwen-14B leads
DeepSeek-R1-Distill-Qwen-14B: 19.2 (#263), GPT-4.1 nano: 8.5 (#349)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| Epoch Capabilities Index | 135.43 | 129.62 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 33.3% |
| ARC-AGI-1 | — | 0% |
| CritPt | — | 0% |
| Chess Puzzles | 1% | — |
| LMArena Hard Prompts | — | 1286 |
| DTBench | — | 52.5% |
| LMCA | — | 5.5% |
Math DeepSeek-R1-Distill-Qwen-14B leads
DeepSeek-R1-Distill-Qwen-14B: 35.5 (#184), GPT-4.1 nano: 26.9 (#252)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 50.6% | 28.9% |
| MATH Level 5 | 87.1% | 70% |
| Omni-MATH | — | 36.7% |
| LMArena Math | — | 1274 |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge DeepSeek-R1-Distill-Qwen-14B leads
DeepSeek-R1-Distill-Qwen-14B: 24.1 (#270), GPT-4.1 nano: 21.8 (#273)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 44.7% | 48.9% |
| SimpleQA Verified | — | 6% |
| MMLU-Pro | — | 55% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1272 |
Multimodal Not comparable
DeepSeek-R1-Distill-Qwen-14B: —, GPT-4.1 nano: 29.2 (#113)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |
Multilingual Not comparable
DeepSeek-R1-Distill-Qwen-14B: —, GPT-4.1 nano: 41.6 (#205)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | — | 1260 |
| LMArena Chinese | — | 1270 |
| LMArena German | — | 1288 |
| LMArena Japanese | — | 1198 |
| LMArena Russian | — | 1261 |
Instruction Following Not comparable
DeepSeek-R1-Distill-Qwen-14B: —, GPT-4.1 nano: 67.8 (#193)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| IFEval | — | 84.3% |
| LMArena Instruction Following | — | 1267 |
Long Context Not comparable
DeepSeek-R1-Distill-Qwen-14B: —, GPT-4.1 nano: 23.7 (#296)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| Fiction.LiveBench | — | 25% |
| LMArena Longer Query | — | 1283 |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Qwen-14B: —, GPT-4.1 nano: 40.5 (#243)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-4.1 nano |
|---|---|---|
| LMArena Text | — | 1285 |
| LMArena Creative Writing | — | 1260 |
| EQ-Bench Creative Writing | — | 946 |
| WildBench | — | 81.2% |
| LMArena Multi-Turn | — | 1277 |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-14B better than GPT-4.1 nano?
DeepSeek-R1-Distill-Qwen-14B is the stronger model overall, scoring 32.7 to 27.9 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-14B or GPT-4.1 nano better for coding?
DeepSeek-R1-Distill-Qwen-14B scores higher on coding benchmarks: 36.9 versus 24.1 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-14B and GPT-4.1 nano share?
4 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-14B has 7 scored results on Noometry and GPT-4.1 nano has 38.