# DeepSeek V4 Flash vs Mercury 2

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 39.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 23.8.
- The biggest single-benchmark swing is WeirdML: 63% for DeepSeek V4 Flash and 43.2% for Mercury 2.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 128K.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 53.6 | 39.1 |
| Rank | 35 | 175 |
| Context | 1M | 128K |
| Input $/M | $0.15 | $0.25 |
| Output $/M | $0.60 | $0.75 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- Mercury 2: 33.5 (#255)

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1582 | 1171 |
| SciCode | 49.9% | 38.7% |
| WeirdML | 63% | 43.2% |
| LMArena Coding | 1457 | 1391 |
| ALE-Bench | 1,306 | 785.58 |
| FrontierCode | 18.8% | — |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- Mercury 2: 23.8 (#170)

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| CritPt | 16.6% | 0.8% |
| LMArena Hard Prompts | 1444 | 1362 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.49 | — |

## Math

- DeepSeek V4 Flash: 60.3 (#37)
- Mercury 2: —

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
| LMArena Math | 1427 | — |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- Mercury 2: 36.2 (#172)

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| LMArena Expert | 1441 | 1358 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
| Vectara Hallucination Rate | — | 12.3% |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- Mercury 2: 46.6 (#157)

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1420 | 1331 |
| LMArena Chinese | 1468 | 1417 |
| LMArena Russian | 1428 | 1304 |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Spanish | 1436 | — |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- Mercury 2: 70.2 (#165)

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1421 | 1329 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- Mercury 2: 40.5 (#154)

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1434 | 1330 |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- Mercury 2: 53.8 (#155)

| Benchmark | DeepSeek V4 Flash | Mercury 2 |
|---|---|---|
| LMArena Text | 1432 | 1355 |
| LMArena Creative Writing | 1403 | 1289 |
| LMArena Multi-Turn | 1449 | 1358 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is DeepSeek V4 Flash better than Mercury 2?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 39.1 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Flash or Mercury 2?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

### Is DeepSeek V4 Flash or Mercury 2 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4 Flash does, with 1M tokens against 128K.

### How many benchmarks do DeepSeek V4 Flash and Mercury 2 share?

16 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Mercury 2 has 17.