# DeepSeek V4 Flash vs Gemini 4 Argon

> Gemini 4 Argon is the stronger model overall, scoring 56.5 to 53.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-gemini-4-argon
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 2 categories and Gemini 4 Argon in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemini 4 Argon leads 62.0 to 47.9.
- The biggest single-benchmark swing is ProofBench: 56% for DeepSeek V4 Flash and 99% for Gemini 4 Argon.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 53.6 | 56.5 |
| Rank | 35 | 24 |
| Context | 1M | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- Gemini 4 Argon: 62.0 (#9)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| LMArena WebDev | 1582 | 1678 |
| SciCode | 49.9% | 61.8% |
| LMArena Coding | 1457 | 1550 |
| FrontierCode | 18.8% | — |
| FrontierSWE | — | 55% |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |

## Agentic & Tool Use

- DeepSeek V4 Flash: —
- Gemini 4 Argon: 49.2 (#8)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | — | 82.2% |
| Vending-Bench 2 | — | 13,718 |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- Gemini 4 Argon: 44.2 (#47)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| CritPt | 16.6% | 27.1% |
| LMArena Hard Prompts | 1444 | 1548 |
| 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)
- Gemini 4 Argon: 73.9 (#17)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| ProofBench | 56% | 99% |
| LMArena Math | 1427 | 1536 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- Gemini 4 Argon: 43.9 (#89)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1441 | 1553 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |

## Multimodal

- DeepSeek V4 Flash: —
- Gemini 4 Argon: 46.5 (#14)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | — | 54.4% |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- Gemini 4 Argon: 60.3 (#1)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1420 | 1523 |
| LMArena Chinese | 1468 | 1610 |
| LMArena Russian | 1428 | 1537 |
| LMArena Spanish | 1436 | 1497 |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- Gemini 4 Argon: 80.1 (#2)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1421 | 1538 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- Gemini 4 Argon: 47.6 (#15)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1434 | 1549 |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- Gemini 4 Argon: 71.4 (#19)

| Benchmark | DeepSeek V4 Flash | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1432 | 1534 |
| LMArena Creative Writing | 1403 | 1531 |
| LMArena Multi-Turn | 1449 | 1557 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is DeepSeek V4 Flash better than Gemini 4 Argon?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 53.6 on the Noometry Index.

### Is DeepSeek V4 Flash or Gemini 4 Argon better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 47.9 in the Noometry coding category.

### How many benchmarks do DeepSeek V4 Flash and Gemini 4 Argon share?

17 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Gemini 4 Argon has 21.