# DeepSeek-V2.5 (Sep 2024) vs DeepSeek V4.1 Flash

> DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-deepseek-v4-1-flash
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and DeepSeek V4.1 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 24.5.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 37.0 | 50.3 |
| Rank | 197 | 40 |
| Context | — | 1M |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- DeepSeek V4.1 Flash: 52.8 (#29)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Coding | 1310 | 1511 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1620 |
| SciCode | — | 51.9% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,092 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- DeepSeek V4.1 Flash: 46.2 (#39)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1485 |
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 14.3% |
| DTBench | — | 89.9% |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| Epoch Capabilities Index | — | 155.01 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- DeepSeek V4.1 Flash: 48.4 (#52)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Math | 1289 | 1493 |
| ProofBench | — | 54% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- DeepSeek V4.1 Flash: 41.6 (#97)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Expert | 1266 | 1505 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- DeepSeek V4.1 Flash: 55.5 (#29)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1452 |
| LMArena Chinese | 1317 | 1506 |
| LMArena French | 1288 | 1448 |
| LMArena Russian | 1289 | 1473 |
| LMArena Spanish | 1248 | 1499 |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- DeepSeek V4.1 Flash: 77.6 (#24)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1280 | 1475 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- DeepSeek V4.1 Flash: 45.2 (#46)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1301 | 1476 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- DeepSeek V4.1 Flash: 65.8 (#43)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1294 | 1465 |
| LMArena Creative Writing | 1285 | 1436 |
| LMArena Multi-Turn | 1297 | 1460 |
| EQ-Bench Creative Writing | — | 1540 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or DeepSeek V4.1 Flash better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and DeepSeek V4.1 Flash share?

14 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and DeepSeek V4.1 Flash has 25.