Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs GPT-4.1
GPT-4.1 has enough public results to be ranked (#215); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and GPT-4.1 in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 34.2.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.7 | 35.7 |
| Released | 2024-05-07 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 10 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141), GPT-4.1: 34.2 (#228)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| WeirdML | — | 39% |
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1391 |
| BigCodeBench Complete | 59.4% | — |
| CadEval | — | 42% |
| ALE-Bench | — | 558.1 |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 34.4 (#40)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 11.7 (#334)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 136.79 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | — | 27% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| EnigmaEval | — | 2.2% |
| LMArena Hard Prompts | — | 1384 |
| DTBench | — | 68.3% |
| LMCA | — | 25.6% |
| BIG-Bench Hard | 78.8% | — |
| ForecastBench | — | 61.5 |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 21.4 (#269)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 6% |
| OTIS Mock AIME 2024-2025 | — | 38.3% |
| Omni-MATH | — | 47.1% |
| LMArena Math | — | 1369 |
| MATH Level 5 | — | 83% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 37.0 (#152)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| GPQA Diamond | — | 66.9% |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | — | 31.1% |
| MMLU-Pro | — | 81.1% |
| Vectara Hallucination Rate | — | 5.6% |
| GPQA (HELM) | — | 65.9% |
| LMArena Expert | — | 1364 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multimodal Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 37.5 (#66)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 72% |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 49.6 (#128)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| LMArena Non-English | — | 1370 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1383 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1320 |
| LMArena Korean | — | 1339 |
| LMArena Russian | — | 1377 |
| LMArena Spanish | — | 1375 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 71.5 (#148)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| IFEval | — | 83.8% |
| LMArena Instruction Following | — | 1367 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 40.0 (#158)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| Fiction.LiveBench | — | 63.9% |
| LMArena Longer Query | — | 1385 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-4.1: 57.8 (#120)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 |
|---|---|---|
| LMArena Text | — | 1383 |
| LMArena Creative Writing | — | 1363 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |
| LMArena Multi-Turn | — | 1398 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than GPT-4.1?
GPT-4.1 has enough public results to be ranked (#215); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or GPT-4.1 better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 34.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and GPT-4.1 share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and GPT-4.1 has 52.