Model comparison
DeepSeek-V3.1 vs GPT-5.4 Pro
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 159× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
DeepSeekSummary
- They share 4 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 0 categories and GPT-5.4 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 27.9.
- The biggest single-benchmark swing is SimpleBench: 40% for DeepSeek-V3.1 and 74.1% for GPT-5.4 Pro.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | GPT-5.4 Pro | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.8 | 58.9 |
| Released | 2025-08-21 | 2026-03-05 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.25 | $30 |
| Output $ / M tokens | $0.95 | $180 |
| Results tracked | 27 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
DeepSeek-V3.1: 40.3 (#144), GPT-5.4 Pro: 43.2 (#90)
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| WeirdML | 38.4% | 57.4% |
| LMArena Coding | 1417 | — |
Reasoning GPT-5.4 Pro leads
DeepSeek-V3.1: 27.9 (#110), GPT-5.4 Pro: 70.7 (#13)
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| SimpleBench | 40% | 74.1% |
| Epoch Capabilities Index | 139.92 | 158.93 |
| ARC-AGI-2 | — | 83.3% |
| Kagi LLM Benchmark | 53.2% | — |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 58.6% |
| EnigmaEval | — | 23.8% |
| LMArena Hard Prompts | 1417 | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
Math GPT-5.4 Pro leads
DeepSeek-V3.1: 38.9 (#122), GPT-5.4 Pro: 72.4 (#22)
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| LMArena Math | 1420 | — |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |
Knowledge GPT-5.4 Pro leads
DeepSeek-V3.1: 43.7 (#90), GPT-5.4 Pro: 68.3 (#7)
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 8.3% |
| GPQA Diamond | — | 94.6% |
| Humanity's Last Exam | — | 44.3% |
| SimpleQA Verified | — | 46.3% |
| LMArena Expert | 1405 | — |
Multilingual Not comparable
DeepSeek-V3.1: 51.6 (#106), GPT-5.4 Pro: —
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Not comparable
DeepSeek-V3.1: 73.9 (#110), GPT-5.4 Pro: —
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1400 | — |
Long Context Not comparable
DeepSeek-V3.1: 36.3 (#232), GPT-5.4 Pro: —
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| Fiction.LiveBench | 52.8% | — |
| LMArena Longer Query | 1422 | — |
Writing & Preference Not comparable
DeepSeek-V3.1: 60.3 (#98), GPT-5.4 Pro: —
| Benchmark | DeepSeek-V3.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1436 | — |
| LMArena Multi-Turn | 1408 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than GPT-5.4 Pro?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 159× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1 or GPT-5.4 Pro?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is DeepSeek-V3.1 or GPT-5.4 Pro better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and GPT-5.4 Pro share?
4 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-5.4 Pro has 16.