# DeepSeek-R1 vs Gemini 1.5 Flash (May 2024)

> DeepSeek-R1 is the stronger model overall, scoring 42.3 to 33.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-r1-vs-gemini-1-5-flash
- Last updated: 2026-10-11
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Gemini 1.5 Flash (May 2024) in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-R1 leads 43.8 to 22.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 16.3% for Gemini 1.5 Flash (May 2024).

## Snapshot

| | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 42.3 | 33.2 |
| Rank | 115 | 246 |
| Context | 164K | — |
| Input $/M | $0.50 | — |
| Output $/M | $2.15 | — |
| Weights | Proprietary | Proprietary |

## Coding

- DeepSeek-R1: 46.3 (#68)
- Gemini 1.5 Flash (May 2024): 34.4 (#236)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| WeirdML | 41.6% | 24.9% |
| LMArena Coding | 1427 | 1261 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| BigCodeBench Instruct | — | 43.5% |
| LiveBench Coding | 66.7% | — |
| BigCodeBench Complete | — | 55.1% |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
| HumanEval+ | — | 75.6% |
| MBPP+ | — | 67.5% |

## Agentic & Tool Use

- DeepSeek-R1: 30.7 (#75)
- Gemini 1.5 Flash (May 2024): 26.6 (#102)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| BALROG | 34.9% | 14.6% |
| DeepResearch Bench | 35.1% | — |
| METR Time Horizons | 53.8% | — |

## Reasoning

- DeepSeek-R1: 18.6 (#278)
- Gemini 1.5 Flash (May 2024): 21.7 (#215)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1257 |
| Epoch Capabilities Index | 141.29 | 129.36 |
| ForecastBench | 60 | 53.9 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| DTBench | — | 53.8% |
| LiveBench Data Analysis | 69.8% | — |
| LiveBench | 71.6% | — |
| PIQA | — | 87.5% |

## Math

- DeepSeek-R1: 43.8 (#79)
- Gemini 1.5 Flash (May 2024): 22.1 (#281)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 16.3% |
| Omni-MATH | 42.4% | 30.4% |
| LMArena Math | 1400 | 1269 |
| MATH Level 5 | 96.6% | 61.9% |
| LiveBench Math | 80.7% | — |
| FrontierMath (Feb 2025 set) | — | 0% |
| GSM8K | — | 82.4% |

## Knowledge

- DeepSeek-R1: 44.5 (#87)
- Gemini 1.5 Flash (May 2024): 26.2 (#260)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| GPQA Diamond | 76.3% | 47.3% |
| MMLU-Pro | 79.3% | 67.8% |
| GPQA (HELM) | 66.6% | 43.7% |
| LMArena Expert | 1394 | 1233 |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| BoolQ | — | 85.8% |
| MMLU | — | 77.9% |

## Multimodal

- DeepSeek-R1: —
- Gemini 1.5 Flash (May 2024): 36.0 (#81)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Vision | — | 1141 |
| Video-MME | — | 70.3% |
| GeoBench | — | 76% |

## Multilingual

- DeepSeek-R1: 52.4 (#85)
- Gemini 1.5 Flash (May 2024): 42.9 (#189)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Non-English | 1412 | 1278 |
| LMArena Chinese | 1442 | 1295 |
| LMArena French | 1417 | 1258 |
| LMArena German | 1404 | 1262 |
| LMArena Japanese | 1391 | 1252 |
| LMArena Korean | 1360 | 1221 |
| LMArena Russian | 1423 | 1288 |
| LMArena Spanish | 1411 | 1243 |

## Instruction Following

- DeepSeek-R1: 72.0 (#143)
- Gemini 1.5 Flash (May 2024): 66.8 (#205)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| IFEval | 78.4% | 83.1% |
| LMArena Instruction Following | 1382 | 1258 |
| LiveBench Instruction Following | 80.5% | — |

## Long Context

- DeepSeek-R1: 45.4 (#36)
- Gemini 1.5 Flash (May 2024): 39.0 (#187)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Longer Query | 1391 | 1284 |
| Fiction.LiveBench | 75% | — |

## Writing & Preference

- DeepSeek-R1: 61.4 (#88)
- Gemini 1.5 Flash (May 2024): 48.7 (#196)

| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Text | 1428 | 1287 |
| LMArena Creative Writing | 1405 | 1285 |
| WildBench | 82.8% | 79.2% |
| LMArena Multi-Turn | 1405 | 1253 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| LiveBench Language | 48.5% | — |

## FAQ

### Is DeepSeek-R1 better than Gemini 1.5 Flash (May 2024)?

DeepSeek-R1 is the stronger model overall, scoring 42.3 to 33.2 on the Noometry Index.

### Is DeepSeek-R1 or Gemini 1.5 Flash (May 2024) better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 34.4 in the Noometry coding category.

### How many benchmarks do DeepSeek-R1 and Gemini 1.5 Flash (May 2024) share?

29 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemini 1.5 Flash (May 2024) has 42.