Model comparison
DeepSeek-R1 vs Gemini 1.5 Flash 8B
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeek
GoogleSummary
- They share 19 benchmarks with published results for both. DeepSeek-R1 scores higher in 7 categories and Gemini 1.5 Flash 8B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-R1 leads 43.8 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 4.6% for Gemini 1.5 Flash 8B.
Side by side
| DeepSeek-R1 | Gemini 1.5 Flash 8B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.3 | 29.9 |
| Released | 2025-01-20 | 2024-10-03 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $2.15 | — |
| Results tracked | 52 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Gemini 1.5 Flash 8B: 35.5 (#225)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Coding | 1427 | 1218 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Gemini 1.5 Flash 8B: —
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Gemini 1.5 Flash 8B leads
DeepSeek-R1: 18.6 (#278), Gemini 1.5 Flash 8B: 20.0 (#244)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1209 |
| 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 | — | 50% |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.29 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Gemini 1.5 Flash 8B: 14.2 (#302)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 4.6% |
| LMArena Math | 1400 | 1207 |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Gemini 1.5 Flash 8B: 16.0 (#289)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| GPQA Diamond | 76.3% | 33% |
| LMArena Expert | 1394 | 1185 |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, Gemini 1.5 Flash 8B: 28.2 (#115)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Vision | — | 1044 |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Gemini 1.5 Flash 8B: 38.5 (#229)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Non-English | 1412 | 1215 |
| LMArena Chinese | 1442 | 1231 |
| LMArena French | 1417 | 1234 |
| LMArena German | 1404 | 1206 |
| LMArena Japanese | 1391 | 1150 |
| LMArena Korean | 1360 | 1140 |
| LMArena Russian | 1423 | 1236 |
| LMArena Spanish | 1411 | 1212 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Gemini 1.5 Flash 8B: 62.8 (#236)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Instruction Following | 1382 | 1199 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Gemini 1.5 Flash 8B: 37.0 (#225)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Longer Query | 1391 | 1219 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Gemini 1.5 Flash 8B: 42.8 (#232)
| Benchmark | DeepSeek-R1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Text | 1428 | 1226 |
| LMArena Creative Writing | 1405 | 1218 |
| LMArena Multi-Turn | 1405 | 1185 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Gemini 1.5 Flash 8B?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.9 on the Noometry Index.
Is DeepSeek-R1 or Gemini 1.5 Flash 8B better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 35.5 in the Noometry coding category.
How many benchmarks do DeepSeek-R1 and Gemini 1.5 Flash 8B share?
19 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemini 1.5 Flash 8B has 21.