# DeepSeek V4 Flash vs Gemini 2.5 Pro

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 45.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-gemini-2-5-pro
- Last updated: 2026-10-11
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 4 categories and Gemini 2.5 Pro in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Flash leads 60.3 to 32.5.
- The biggest single-benchmark swing is ARC-AGI-2: 61.4% for DeepSeek V4 Flash and 4.9% for Gemini 2.5 Pro.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 53.6 | 45.0 |
| Rank | 35 | 75 |
| Context | 1M | 1.05M |
| Input $/M | $0.15 | $1.25 |
| Output $/M | $0.60 | $10 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- Gemini 2.5 Pro: 42.4 (#101)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena WebDev | 1582 | 1227 |
| SciCode | 49.9% | 42.8% |
| WeirdML | 63% | 54% |
| LMArena Coding | 1457 | 1452 |
| ALE-Bench | 1,306 | 785.52 |
| SWE-bench Verified | — | 57.6% |
| FrontierCode | 18.8% | — |
| SWE-bench Verified (bash only) | — | 53.6% |
| Aider Polyglot | — | 83.1% |
| GSO | — | 3.9% |
| LiveBench Coding | — | 85.9% |
| CadEval | — | 64% |
| AlgoTune | — | 1.51 |

## Agentic & Tool Use

- DeepSeek V4 Flash: —
- Gemini 2.5 Pro: 29.2 (#88)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| Terminal-Bench | — | 32.6% |
| GDPval | — | 23.3% |
| Remote Labor Index | — | 0.8% |
| TheAgentCompany | — | 30.3% |
| τ²-bench Banking | — | 13.7% |
| DeepResearch Bench | — | 42.8% |
| BALROG | — | 43.3% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 55.4% |
| Vending-Bench 2 | — | 573.64 |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- Gemini 2.5 Pro: 28.8 (#99)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| ARC-AGI-2 | 61.4% | 4.9% |
| SimpleBench | 61.1% | 62.4% |
| Kagi LLM Benchmark | 52.2% | 70.3% |
| ARC-AGI-1 | 89% | 41% |
| CritPt | 16.6% | 2% |
| Chess Puzzles | 33% | 20% |
| LMArena Hard Prompts | 1444 | 1455 |
| DTBench | 90.9% | 82.4% |
| LMCA | 41.7% | 34.8% |
| Epoch Capabilities Index | 154.49 | 145.32 |
| NYT Connections (extended) | 89.6% | — |
| EnigmaEval | — | 5.6% |
| LiveBench Reasoning | — | 89.8% |
| Mystery Game Puzzles | 34% | — |
| LiveBench Data Analysis | — | 79.9% |
| ForecastBench | — | 61.3 |
| LiveBench | — | 82.3% |

## Math

- DeepSeek V4 Flash: 60.3 (#37)
- Gemini 2.5 Pro: 32.5 (#213)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.5% | 24.6% |
| FrontierMath Tier 4 | 24.4% | 0% |
| OTIS Mock AIME 2024-2025 | 94.4% | 84.7% |
| LMArena Math | 1427 | 1450 |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |
| Omni-MATH | — | 41.6% |
| LiveBench Math | — | 90.2% |
| MATH Level 5 | — | 95.9% |
| FrontierMath (Feb 2025 set) | — | 14.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- Gemini 2.5 Pro: 56.0 (#46)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| GPQA Diamond | 91% | 85.3% |
| LMArena Expert | 1441 | 1452 |
| Humanity's Last Exam | — | 21.6% |
| SimpleQA Verified | 33.6% | — |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.6% |
| Vectara Hallucination Rate | — | 7% |
| GPQA (HELM) | — | 74.9% |

## Multimodal

- DeepSeek V4 Flash: —
- Gemini 2.5 Pro: 45.2 (#18)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | — | 1263 |
| GeoBench | — | 86% |
| VPCT | — | 48% |
| LMArena Document | — | 1421 |
| SpatialViz-Bench | — | 44.7% |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- Gemini 2.5 Pro: 55.3 (#31)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1420 | 1451 |
| LMArena Chinese | 1468 | 1507 |
| LMArena French | 1439 | 1472 |
| LMArena German | 1418 | 1487 |
| LMArena Japanese | 1406 | 1461 |
| LMArena Korean | 1384 | 1434 |
| LMArena Russian | 1428 | 1461 |
| LMArena Spanish | 1436 | 1473 |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- Gemini 2.5 Pro: 75.0 (#75)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1421 | 1437 |
| LiveBench Instruction Following | — | 80.6% |
| IFEval | — | 84% |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- Gemini 2.5 Pro: 59.8 (#5)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1434 | 1449 |
| Fiction.LiveBench | — | 91.7% |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- Gemini 2.5 Pro: 63.7 (#62)

| Benchmark | DeepSeek V4 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1432 | 1458 |
| LMArena Creative Writing | 1403 | 1454 |
| EQ-Bench Creative Writing | 1559 | 1421 |
| LMArena Multi-Turn | 1449 | 1453 |
| Short-Story Creative Writing | — | 83.8% |
| WildBench | — | 85.7% |
| LiveBench Language | — | 67.8% |

## FAQ

### Is DeepSeek V4 Flash better than Gemini 2.5 Pro?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 45.0 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Flash or Gemini 2.5 Pro?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is DeepSeek V4 Flash or Gemini 2.5 Pro better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 1M.

### How many benchmarks do DeepSeek V4 Flash and Gemini 2.5 Pro share?

35 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Gemini 2.5 Pro has 78.