Model comparison
DeepSeek-R1 vs Gemini 3.6 Flash
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 42.3 on the Noometry Index. DeepSeek-R1 costs 1.6× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
DeepSeek
GoogleSummary
- They share 27 benchmarks with published results for both. DeepSeek-R1 scores higher in 1 category and Gemini 3.6 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-1: 21.2% for DeepSeek-R1 and 91.2% for Gemini 3.6 Flash.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-R1 | Gemini 3.6 Flash | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.3 | 54.1 |
| Released | 2025-01-20 | 2026-07-21 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.50 | $0.75 |
| Output $ / M tokens | $2.15 | $3.75 |
| Results tracked | 52 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
DeepSeek-R1: 46.3 (#68), Gemini 3.6 Flash: 50.0 (#48)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| SciCode | 35.7% | 52.7% |
| WeirdML | 41.6% | 56.1% |
| LMArena Coding | 1427 | 1491 |
| ALE-Bench | 804.12 | 715.52 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1538 |
| LiveBench Coding | 66.7% | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Gemini 3.6 Flash leads
DeepSeek-R1: 30.7 (#75), Gemini 3.6 Flash: 32.3 (#65)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | — | 46.9% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| GDP.pdf | — | 14% |
| METR Time Horizons | 53.8% | — |
Reasoning Gemini 3.6 Flash leads
DeepSeek-R1: 18.6 (#278), Gemini 3.6 Flash: 58.8 (#22)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| ARC-AGI-2 | 1.3% | 60.4% |
| ARC-AGI-1 | 21.2% | 91.2% |
| CritPt | 1.1% | 10.6% |
| LMArena Hard Prompts | 1416 | 1485 |
| Epoch Capabilities Index | 141.29 | 154.25 |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 89% |
| Chess Puzzles | — | 43% |
| LiveBench Reasoning | 83.2% | — |
| Mystery Game Puzzles | — | 30% |
| DTBench | — | 95.5% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 44.9% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Gemini 3.6 Flash leads
DeepSeek-R1: 43.8 (#79), Gemini 3.6 Flash: 57.3 (#40)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 94.2% |
| LMArena Math | 1400 | 1505 |
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| ProofBench | — | 36% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge Gemini 3.6 Flash leads
DeepSeek-R1: 44.5 (#87), Gemini 3.6 Flash: 67.8 (#8)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 76.3% | 94.1% |
| LMArena Expert | 1394 | 1488 |
| SimpleQA Verified | — | 66.2% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, Gemini 3.6 Flash: 38.5 (#64)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | — | 1298 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |
| LMArena Document | — | 1456 |
Multilingual Gemini 3.6 Flash leads
DeepSeek-R1: 52.4 (#85), Gemini 3.6 Flash: 56.5 (#19)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1412 | 1469 |
| LMArena Chinese | 1442 | 1531 |
| LMArena French | 1417 | 1504 |
| LMArena German | 1404 | 1478 |
| LMArena Japanese | 1391 | 1476 |
| LMArena Korean | 1360 | 1431 |
| LMArena Russian | 1423 | 1487 |
| LMArena Spanish | 1411 | 1475 |
Instruction Following Gemini 3.6 Flash leads
DeepSeek-R1: 72.0 (#143), Gemini 3.6 Flash: 77.0 (#33)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1382 | 1466 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context Too close to call
DeepSeek-R1: 45.4 (#36), Gemini 3.6 Flash: 45.1 (#50)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1391 | 1474 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Gemini 3.6 Flash leads
DeepSeek-R1: 61.4 (#88), Gemini 3.6 Flash: 68.2 (#27)
| Benchmark | DeepSeek-R1 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1428 | 1479 |
| LMArena Creative Writing | 1405 | 1465 |
| EQ-Bench Creative Writing | 1500 | 1604 |
| LMArena Multi-Turn | 1405 | 1481 |
| Short-Story Creative Writing | 83% | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Gemini 3.6 Flash?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 42.3 on the Noometry Index. DeepSeek-R1 costs 1.6× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or Gemini 3.6 Flash?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.
Is DeepSeek-R1 or Gemini 3.6 Flash better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 46.3 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.6 Flash does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-R1 and Gemini 3.6 Flash share?
27 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemini 3.6 Flash has 46.