Model comparison
DeepSeek-V3.1-Terminus vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 3.7× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and GPT-5.4 mini in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 38.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 37.9% for GPT-5.4 mini.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | GPT-5.4 mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 43.1 | 45.0 |
| Released | 2025-09-22 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 164K | 400K |
| Max output | 147K | 128K |
| Input $ / M tokens | $0.27 | $0.75 |
| Output $ / M tokens | $1 | $4.50 |
| Results tracked | 16 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
DeepSeek-V3.1-Terminus: 42.0 (#113), GPT-5.4 mini: 45.2 (#72)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| SciCode | 40.6% | 49.9% |
| LMArena Coding | 1426 | 1438 |
| ALE-Bench | 745.17 | 1,189 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| WeirdML | — | 60.3% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, GPT-5.4 mini: 29.9 (#81)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
DeepSeek-V3.1-Terminus: 26.4 (#133), GPT-5.4 mini: 30.4 (#85)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 37.9% |
| CritPt | 1.7% | 10% |
| LMArena Hard Prompts | 1426 | 1424 |
| DTBench | 81.3% | 80% |
| LMCA | 28.6% | 40.8% |
| ARC-AGI-2 | — | 18.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| Epoch Capabilities Index | — | 148.84 |
| ForecastBench | — | 57 |
Math GPT-5.4 mini leads
DeepSeek-V3.1-Terminus: 38.5 (#137), GPT-5.4 mini: 45.5 (#75)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| LMArena Math | 1402 | 1419 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 21% |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, GPT-5.4 mini: 51.5 (#67)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | — | 86.9% |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |
| LMArena Expert | — | 1435 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, GPT-5.4 mini: 39.7 (#56)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Too close to call
DeepSeek-V3.1-Terminus: 52.1 (#92), GPT-5.4 mini: 51.9 (#96)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1407 | 1405 |
| LMArena Russian | 1436 | 1417 |
| LMArena Chinese | — | 1446 |
| LMArena French | — | 1440 |
| LMArena German | — | 1409 |
| LMArena Japanese | — | 1374 |
| LMArena Korean | — | 1368 |
| LMArena Spanish | — | 1405 |
Instruction Following Too close to call
DeepSeek-V3.1-Terminus: 74.0 (#106), GPT-5.4 mini: 74.1 (#102)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1404 | 1405 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.4 (#97), GPT-5.4 mini: 43.0 (#112)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1421 | 1407 |
Writing & Preference GPT-5.4 mini leads
DeepSeek-V3.1-Terminus: 61.0 (#92), GPT-5.4 mini: 64.0 (#58)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1419 | 1412 |
| LMArena Creative Writing | 1403 | 1370 |
| LMArena Multi-Turn | 1411 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 3.7× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or GPT-5.4 mini?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is DeepSeek-V3.1-Terminus or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and GPT-5.4 mini share?
16 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GPT-5.4 mini has 46.