# DeepSeek V4 Flash vs GPT-4.1 mini

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 33.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-gpt-4-1-mini
- Last updated: 2026-10-12
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and GPT-4.1 mini in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 10.8.
- The biggest single-benchmark swing is ARC-AGI-1: 89% for DeepSeek V4 Flash and 3.5% for GPT-4.1 mini.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 53.6 | 33.6 |
| Rank | 35 | 240 |
| Context | 1M | 1.05M |
| Input $/M | $0.15 | $0.40 |
| Output $/M | $0.60 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- GPT-4.1 mini: 30.6 (#293)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| SciCode | 49.9% | 40.4% |
| WeirdML | 63% | 37.6% |
| LMArena Coding | 1457 | 1367 |
| FrontierCode | 18.8% | — |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| LMArena WebDev | 1582 | — |
| BigCodeBench Instruct | — | 48.9% |
| CadEval | — | 16% |
| ALE-Bench | 1,306 | — |

## Agentic & Tool Use

- DeepSeek V4 Flash: —
- GPT-4.1 mini: 33.3 (#55)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 50.5% |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- GPT-4.1 mini: 10.8 (#340)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| ARC-AGI-2 | 61.4% | 0% |
| Kagi LLM Benchmark | 52.2% | 48.6% |
| ARC-AGI-1 | 89% | 3.5% |
| CritPt | 16.6% | 0% |
| Chess Puzzles | 33% | 7% |
| LMArena Hard Prompts | 1444 | 1349 |
| Mystery Game Puzzles | 34% | 7% |
| DTBench | 90.9% | 68.8% |
| LMCA | 41.7% | 21.1% |
| Epoch Capabilities Index | 154.49 | 135.01 |
| SimpleBench | 61.1% | — |
| NYT Connections (extended) | 89.6% | — |

## Math

- DeepSeek V4 Flash: 60.3 (#37)
- GPT-4.1 mini: 24.1 (#270)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.5% | 6.7% |
| OTIS Mock AIME 2024-2025 | 94.4% | 44.7% |
| LMArena Math | 1427 | 1343 |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |
| Omni-MATH | — | 49.1% |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- GPT-4.1 mini: 34.7 (#194)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 91% | 65.8% |
| SimpleQA Verified | 33.6% | 12.7% |
| LMArena Expert | 1441 | 1338 |
| MMLU-Pro | — | 78.3% |
| GPQA (HELM) | — | 61.4% |

## Multimodal

- DeepSeek V4 Flash: —
- GPT-4.1 mini: 35.8 (#82)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | — | 1181 |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- GPT-4.1 mini: 45.7 (#166)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1420 | 1318 |
| LMArena Chinese | 1468 | 1329 |
| LMArena French | 1439 | 1358 |
| LMArena German | 1418 | 1351 |
| LMArena Japanese | 1406 | 1290 |
| LMArena Korean | 1384 | 1298 |
| LMArena Russian | 1428 | 1324 |
| LMArena Spanish | 1436 | 1319 |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- GPT-4.1 mini: 73.7 (#118)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Instruction Following | 1421 | 1333 |
| IFEval | — | 90.4% |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- GPT-4.1 mini: 31.8 (#275)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1434 | 1344 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- GPT-4.1 mini: 48.6 (#199)

| Benchmark | DeepSeek V4 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1432 | 1340 |
| LMArena Creative Writing | 1403 | 1300 |
| EQ-Bench Creative Writing | 1559 | 1147 |
| LMArena Multi-Turn | 1449 | 1354 |
| WildBench | — | 83.8% |

## FAQ

### Is DeepSeek V4 Flash better than GPT-4.1 mini?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 33.6 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Flash or GPT-4.1 mini?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

### Is DeepSeek V4 Flash or GPT-4.1 mini better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 30.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 1M.

### How many benchmarks do DeepSeek V4 Flash and GPT-4.1 mini share?

33 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and GPT-4.1 mini has 47.