# DeepSeek-V2.5 (Sep 2024) vs GPT-5.4 mini

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-gpt-5-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and GPT-5.4 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 34.2.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 37.0 | 44.8 |
| Rank | 197 | 69 |
| Context | — | 400K |
| Input $/M | — | $0.75 |
| Output $/M | — | $4.50 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- GPT-5.4 mini: 45.0 (#67)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1310 | 1438 |
| FrontierCode | — | 27% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- GPT-5.4 mini: 29.6 (#74)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- GPT-5.4 mini: 30.3 (#77)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1424 |
| ARC-AGI-2 | — | 18.9% |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| DTBench | — | 80% |
| LMCA | — | 40.8% |
| Epoch Capabilities Index | — | 148.83 |
| ForecastBench | — | 57 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- GPT-5.4 mini: 45.4 (#63)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Math | 1289 | 1418 |
| 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

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- GPT-5.4 mini: 51.4 (#62)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Expert | 1266 | 1434 |
| GPQA Diamond | — | 86.9% |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |

## Multimodal

- DeepSeek-V2.5 (Sep 2024): —
- GPT-5.4 mini: 39.0 (#51)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- GPT-5.4 mini: 52.1 (#94)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1273 | 1405 |
| LMArena Chinese | 1317 | 1446 |
| LMArena French | 1288 | 1440 |
| LMArena German | 1258 | 1407 |
| LMArena Japanese | 1228 | 1375 |
| LMArena Korean | 1209 | 1369 |
| LMArena Russian | 1289 | 1417 |
| LMArena Spanish | 1248 | 1403 |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- GPT-5.4 mini: 74.3 (#99)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1280 | 1405 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- GPT-5.4 mini: 42.9 (#107)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1301 | 1407 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- GPT-5.4 mini: 64.2 (#56)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1294 | 1411 |
| LMArena Creative Writing | 1285 | 1370 |
| LMArena Multi-Turn | 1297 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than GPT-5.4 mini?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or GPT-5.4 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GPT-5.4 mini share?

17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GPT-5.4 mini has 46.