Model comparison
DeepSeek-V3.1-Terminus vs GPT-4 Turbo
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeekSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and GPT-4 Turbo in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 38.5 to 9.0.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 61.6% for GPT-4 Turbo.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | GPT-4 Turbo | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 43.1 | 30.5 |
| Released | 2025-09-22 | 2023-11-06 |
| Weights | Open | Proprietary |
| Context window | 164K | 128K |
| Max output | 147K | 4K |
| Input $ / M tokens | $0.27 | $10 |
| Output $ / M tokens | $1 | $30 |
| Results tracked | 16 | 36 |
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: 42.0 (#113), GPT-4 Turbo: 33.8 (#249)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Coding | 1426 | 1268 |
| SciCode | 40.6% | — |
| WeirdML | — | 18% |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 58.2% |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, GPT-4 Turbo: —
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), GPT-4 Turbo: 15.3 (#317)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1251 |
| DTBench | 81.3% | 61.6% |
| LMCA | 28.6% | 9.8% |
| SimpleBench | — | 25.1% |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | — | 6% |
| Epoch Capabilities Index | — | 127.25 |
| ForecastBench | — | 59.4 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), GPT-4 Turbo: 9.0 (#322)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Math | 1402 | 1272 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| MATH Level 5 | — | 46.7% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, GPT-4 Turbo: 24.3 (#268)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | — | 46.6% |
| Confabulations | — | 28.4% |
| LMArena Expert | — | 1223 |
| MMLU | — | 81.3% |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, GPT-4 Turbo: 30.6 (#110)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), GPT-4 Turbo: 40.5 (#216)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1407 | 1245 |
| LMArena Russian | 1436 | 1259 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1276 |
| LMArena German | — | 1259 |
| LMArena Japanese | — | 1194 |
| LMArena Korean | — | 1187 |
| LMArena Spanish | — | 1260 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), GPT-4 Turbo: 65.8 (#216)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1404 | 1249 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), GPT-4 Turbo: 38.0 (#206)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1421 | 1254 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), GPT-4 Turbo: 47.7 (#206)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1419 | 1272 |
| LMArena Creative Writing | 1403 | 1269 |
| LMArena Multi-Turn | 1411 | 1267 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than GPT-4 Turbo?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.5 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or GPT-4 Turbo?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is DeepSeek-V3.1-Terminus or GPT-4 Turbo better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.1-Terminus and GPT-4 Turbo share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GPT-4 Turbo has 36.