Model comparison
DeepSeek-V3.1 vs GPT-4o
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 28.6 on the Noometry Index.
Last verified . 25 shared benchmarks.
DeepSeekSummary
- They share 25 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and GPT-4o in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 10.6.
- The biggest single-benchmark swing is SimpleBench: 40% for DeepSeek-V3.1 and 17.8% for GPT-4o.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | GPT-4o | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.8 | 28.6 |
| Released | 2025-08-21 | 2024-05-13 |
| Weights | Open | Proprietary |
| Context window | 164K | 128K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.25 | $2.50 |
| Output $ / M tokens | $0.95 | $10 |
| Results tracked | 27 | 72 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), GPT-4o: 24.8 (#328)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| WeirdML | 38.4% | 25.1% |
| LMArena Coding | 1417 | 1297 |
| SWE-bench Verified | — | 31% |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| GSO | — | 0% |
| BigCodeBench Instruct | — | 51.1% |
| LiveBench Coding | — | 51.4% |
| BigCodeBench Complete | — | 61.1% |
| CadEval | — | 26% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, GPT-4o: 21.0 (#141)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), GPT-4o: 9.4 (#343)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| SimpleBench | 40% | 17.8% |
| LMArena Hard Prompts | 1417 | 1281 |
| DTBench | 82.7% | 64.5% |
| LMCA | 24.3% | 16.6% |
| Epoch Capabilities Index | 139.92 | 128.97 |
| ForecastBench | 58 | 57.7 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | 53.2% | — |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| EnigmaEval | — | 0.8% |
| LiveBench Reasoning | — | 55.8% |
| LiveBench Data Analysis | — | 60.9% |
| LiveBench | — | 55.3% |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), GPT-4o: 10.6 (#312)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| LMArena Math | 1420 | 1285 |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| OTIS Mock AIME 2024-2025 | — | 6.4% |
| Omni-MATH | — | 29.3% |
| LiveBench Math | — | 49.5% |
| MATH Level 5 | — | 53.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), GPT-4o: 28.8 (#242)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 9.6% |
| LMArena Expert | 1405 | 1250 |
| GPQA Diamond | — | 49.2% |
| Humanity's Last Exam | — | 2.7% |
| SimpleQA Verified | — | 26% |
| MMLU-Pro | — | 71.3% |
| Confabulations | — | 15.3% |
| GPQA (HELM) | — | 52% |
| MMLU | — | 88.1% |
Multimodal Not comparable
DeepSeek-V3.1: —, GPT-4o: 34.5 (#91)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| LMArena Vision | — | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), GPT-4o: 43.2 (#186)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| LMArena Non-English | 1400 | 1283 |
| LMArena Chinese | 1469 | 1277 |
| LMArena French | 1447 | 1304 |
| LMArena German | 1411 | 1282 |
| LMArena Japanese | 1378 | 1257 |
| LMArena Korean | 1337 | 1234 |
| LMArena Russian | 1405 | 1286 |
| LMArena Spanish | 1431 | 1292 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), GPT-4o: 66.6 (#207)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| LMArena Instruction Following | 1400 | 1278 |
| LiveBench Instruction Following | — | 68.6% |
| IFEval | — | 81.7% |
Long Context GPT-4o leads
DeepSeek-V3.1: 36.3 (#232), GPT-4o: 39.4 (#179)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| Fiction.LiveBench | 52.8% | 66.7% |
| LMArena Longer Query | 1422 | 1289 |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), GPT-4o: 52.6 (#166)
| Benchmark | DeepSeek-V3.1 | GPT-4o |
|---|---|---|
| LMArena Text | 1420 | 1300 |
| LMArena Creative Writing | 1401 | 1292 |
| LMArena Multi-Turn | 1408 | 1302 |
| Short-Story Creative Writing | — | 81.8% |
| EQ-Bench Creative Writing | 1436 | — |
| WildBench | — | 82.8% |
| LiveBench Language | — | 47.6% |
Frequently asked questions
Is DeepSeek-V3.1 better than GPT-4o?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 28.6 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1 or GPT-4o?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GPT-4o lists at $2.50 and $10.
Is DeepSeek-V3.1 or GPT-4o better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 24.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1 does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.1 and GPT-4o share?
25 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-4o has 72.