Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs GPT-5
GPT-5 has enough public results to be ranked (#37); 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 0 categories and GPT-5 in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5 leads 50.7 to 39.8.
- 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-5 | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.7 | 50.9 |
| Released | 2024-05-07 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 10 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141), GPT-5: 50.7 (#39)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| SWE-bench Verified | — | 73.6% |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| LMArena WebDev | — | 1417 |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
| WeirdML | — | 60.7% |
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1436 |
| BigCodeBench Complete | 59.4% | — |
| ALE-Bench | — | 1,162 |
| AlgoTune | — | 1.67 |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 33.0 (#53)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 38.3 (#55)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 150 |
| ARC-AGI-2 | — | 9.9% |
| SimpleBench | — | 56.7% |
| Kagi LLM Benchmark | — | 72.7% |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
| Chess Puzzles | — | 37% |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| LMArena Hard Prompts | — | 1415 |
| Mystery Game Puzzles | — | 23% |
| DTBench | — | 90.7% |
| LMCA | — | 40% |
| BIG-Bench Hard | 78.8% | — |
| ForecastBench | — | 61.4 |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 54.6 (#36)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 55.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 91.4% |
| ProofBench | — | 18% |
| Omni-MATH | — | 64.7% |
| LMArena Math | — | 1406 |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 56.5 (#37)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| GPQA Diamond | — | 86.2% |
| Humanity's Last Exam | — | 25.3% |
| SimpleQA Verified | — | 50.1% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| Vectara Hallucination Rate | — | 14.7% |
| GPQA (HELM) | — | 79.2% |
| LMArena Expert | — | 1420 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multimodal Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 46.1 (#12)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| LMArena Vision | — | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 51.5 (#105)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| LMArena Non-English | — | 1397 |
| LMArena Chinese | — | 1423 |
| LMArena French | — | 1409 |
| LMArena German | — | 1415 |
| LMArena Japanese | — | 1411 |
| LMArena Korean | — | 1361 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1398 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 74.0 (#107)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| IFEval | — | 87.5% |
| LMArena Instruction Following | — | 1388 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 69.5 (#2)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | — | 1399 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-5: 63.5 (#63)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5 |
|---|---|---|
| LMArena Text | — | 1406 |
| LMArena Creative Writing | — | 1365 |
| Short-Story Creative Writing | — | 86% |
| EQ-Bench Creative Writing | — | 1627 |
| WildBench | — | 85.7% |
| LMArena Multi-Turn | — | 1426 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than GPT-5?
GPT-5 has enough public results to be ranked (#37); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or GPT-5 better for coding?
GPT-5 scores higher on coding benchmarks: 50.7 versus 39.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and GPT-5 share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and GPT-5 has 69.