Model comparison
DeepSeek-R1 vs Gemini 2.5 Flash-Lite
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 5.2× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
DeepSeek
GoogleSummary
- They share 28 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Gemini 2.5 Flash-Lite in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where DeepSeek-R1 leads 45.4 to 33.3.
- The biggest single-benchmark swing is GPQA (HELM): 66.6% for DeepSeek-R1 and 30.9% for Gemini 2.5 Flash-Lite.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-R1 | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.3 | 37.0 |
| Released | 2025-01-20 | 2025-06-17 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.50 | $0.10 |
| Output $ / M tokens | $2.15 | $0.40 |
| Results tracked | 52 | 33 |
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 2.5 Flash-Lite: 38.5 (#173)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| WeirdML | 41.6% | 35.2% |
| LMArena Coding | 1427 | 1373 |
| ALE-Bench | 804.12 | 325.9 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| LiveBench Coding | 66.7% | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use DeepSeek-R1 leads
DeepSeek-R1: 30.7 (#75), Gemini 2.5 Flash-Lite: 28.0 (#96)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 36.9% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Gemini 2.5 Flash-Lite leads
DeepSeek-R1: 18.6 (#278), Gemini 2.5 Flash-Lite: 22.2 (#205)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Kagi LLM Benchmark | 69.4% | 40.5% |
| LMArena Hard Prompts | 1416 | 1377 |
| Epoch Capabilities Index | 141.29 | 133.94 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| DTBench | — | 62.8% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 18.1% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Gemini 2.5 Flash-Lite: 38.0 (#144)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Omni-MATH | 42.4% | 48% |
| LMArena Math | 1400 | 1373 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Gemini 2.5 Flash-Lite: 32.5 (#210)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| MMLU-Pro | 79.3% | 53.7% |
| Vectara Hallucination Rate | 11.3% | 3.3% |
| GPQA (HELM) | 66.6% | 30.9% |
| LMArena Expert | 1394 | 1373 |
| GPQA Diamond | 76.3% | — |
| Confabulations | 12.7% | — |
Multimodal Not comparable
DeepSeek-R1: —, Gemini 2.5 Flash-Lite: 29.1 (#114)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1198 |
| VPCT | — | 30% |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Gemini 2.5 Flash-Lite: 49.3 (#134)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1412 | 1369 |
| LMArena Chinese | 1442 | 1404 |
| LMArena French | 1417 | 1388 |
| LMArena German | 1404 | 1389 |
| LMArena Japanese | 1391 | 1359 |
| LMArena Korean | 1360 | 1360 |
| LMArena Russian | 1423 | 1373 |
| LMArena Spanish | 1411 | 1396 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Gemini 2.5 Flash-Lite: 70.0 (#168)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| IFEval | 78.4% | 81% |
| LMArena Instruction Following | 1382 | 1367 |
| LiveBench Instruction Following | 80.5% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Gemini 2.5 Flash-Lite: 33.3 (#262)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Fiction.LiveBench | 75% | 47.2% |
| LMArena Longer Query | 1391 | 1373 |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Gemini 2.5 Flash-Lite: 56.8 (#135)
| Benchmark | DeepSeek-R1 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1428 | 1379 |
| LMArena Creative Writing | 1405 | 1367 |
| WildBench | 82.8% | 81.8% |
| LMArena Multi-Turn | 1405 | 1366 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Gemini 2.5 Flash-Lite?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 5.2× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or Gemini 2.5 Flash-Lite?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Gemini 2.5 Flash-Lite better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 38.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-R1 and Gemini 2.5 Flash-Lite share?
28 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.