# DeepSeek V4 Flash vs Gemini 1.0 Pro

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-gemini-1-0-pro
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Gemini 1.0 Pro in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Flash leads 60.0 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for DeepSeek V4 Flash and 1.1% for Gemini 1.0 Pro.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 53.6 | 27.1 |
| Rank | 32 | 327 |
| Context | 1M | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.6 (#56)
- Gemini 1.0 Pro: 31.6 (#270)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1457 | 1108 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1581 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
| HumanEval+ | — | 55.5% |
| MBPP+ | — | 61.4% |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#25)
- Gemini 1.0 Pro: 16.4 (#292)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1109 |
| DTBench | 90.9% | 45.9% |
| Epoch Capabilities Index | 154.51 | 116.97 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| LMCA | 41.7% | — |

## Math

- DeepSeek V4 Flash: 60.0 (#31)
- Gemini 1.0 Pro: 8.7 (#315)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 1.1% |
| LMArena Math | 1427 | 1132 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |
| MATH Level 5 | — | 11.2% |

## Knowledge

- DeepSeek V4 Flash: 55.5 (#43)
- Gemini 1.0 Pro: 15.5 (#286)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | 91% | 34% |
| LMArena Expert | 1441 | 1059 |
| SimpleQA Verified | 33.6% | — |
| MMLU | — | 70% |

## Multilingual

- DeepSeek V4 Flash: 53.2 (#71)
- Gemini 1.0 Pro: 33.5 (#247)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1420 | 1138 |
| LMArena Chinese | 1467 | 1124 |
| LMArena French | 1438 | 1144 |
| LMArena German | 1418 | 1125 |
| LMArena Japanese | 1403 | 1023 |
| LMArena Russian | 1428 | 1186 |
| LMArena Spanish | 1437 | 1118 |
| LMArena Korean | 1383 | — |

## Instruction Following

- DeepSeek V4 Flash: 75.1 (#76)
- Gemini 1.0 Pro: 57.9 (#262)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1421 | 1114 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#81)
- Gemini 1.0 Pro: 34.3 (#244)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1435 | 1132 |

## Writing & Preference

- DeepSeek V4 Flash: 64.0 (#59)
- Gemini 1.0 Pro: 36.2 (#259)

| Benchmark | DeepSeek V4 Flash | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1432 | 1149 |
| LMArena Creative Writing | 1403 | 1130 |
| LMArena Multi-Turn | 1449 | 1139 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is DeepSeek V4 Flash better than Gemini 1.0 Pro?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 27.1 on the Noometry Index.

### Is DeepSeek V4 Flash or Gemini 1.0 Pro better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 31.6 in the Noometry coding category.

### How many benchmarks do DeepSeek V4 Flash and Gemini 1.0 Pro share?

20 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Gemini 1.0 Pro has 24.