Model comparison
DeepSeek-V3.1-Terminus vs GPT-4.1
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 35.7 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and GPT-4.1 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 35.7 to 21.4.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 68.3% for GPT-4.1.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | GPT-4.1 | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.6 | 35.7 |
| Released | 2025-09-22 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.30 | $2 |
| Output $ / M tokens | $1 | $8 |
| Results tracked | 16 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), GPT-4.1: 34.2 (#228)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| LMArena Coding | 1426 | 1391 |
| ALE-Bench | 745.17 | 558.1 |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| SciCode | 40.6% | — |
| WeirdML | — | 39% |
| CadEval | — | 42% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, GPT-4.1: 34.4 (#40)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), GPT-4.1: 11.7 (#334)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 52.3% |
| LMArena Hard Prompts | 1427 | 1384 |
| DTBench | 81.3% | 68.3% |
| LMCA | 28.6% | 25.6% |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | — | 27% |
| ARC-AGI-1 | — | 5.5% |
| CritPt | 1.7% | — |
| Chess Puzzles | — | 6% |
| EnigmaEval | — | 2.2% |
| Epoch Capabilities Index | — | 136.79 |
| ForecastBench | — | 61.5 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), GPT-4.1: 21.4 (#269)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| LMArena Math | 1402 | 1369 |
| FrontierMath (Tiers 1-3) | — | 6% |
| OTIS Mock AIME 2024-2025 | — | 38.3% |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, GPT-4.1: 37.0 (#152)
| Benchmark | DeepSeek-V3.1-Terminus | 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 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, GPT-4.1: 37.5 (#66)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 72% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), GPT-4.1: 49.6 (#128)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1407 | 1370 |
| LMArena Russian | 1434 | 1377 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1383 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1320 |
| LMArena Korean | — | 1339 |
| LMArena Spanish | — | 1375 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), GPT-4.1: 71.5 (#148)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1367 |
| IFEval | — | 83.8% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), GPT-4.1: 40.0 (#158)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1426 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), GPT-4.1: 57.8 (#120)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4.1 |
|---|---|---|
| LMArena Text | 1420 | 1383 |
| LMArena Creative Writing | 1404 | 1363 |
| LMArena Multi-Turn | 1411 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than GPT-4.1?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 35.7 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or GPT-4.1?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; GPT-4.1 lists at $2 and $8.
Is DeepSeek-V3.1-Terminus or GPT-4.1 better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and GPT-4.1 share?
14 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GPT-4.1 has 52.