Model comparison
DeepSeek-R1 vs Gemma 2 27B
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.4 on the Noometry Index.
Last verified . 29 shared benchmarks.
DeepSeek
GoogleSummary
- They share 29 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Gemma 2 27B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-R1 leads 43.8 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 96.6% for DeepSeek-R1 and 27.9% for Gemma 2 27B.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- DeepSeek-R1 accepts more context: 164K tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Gemma 2 27B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.3 | 29.4 |
| Released | 2025-01-20 | 2024-06-24 |
| Weights | Proprietary | Open |
| Context window | 164K | 8K |
| Max output | 64K | 2K |
| Input $ / M tokens | $0.50 | $0.65 |
| Output $ / M tokens | $2.15 | $0.65 |
| Results tracked | 52 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Gemma 2 27B: 34.1 (#246)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| LiveBench Coding | 66.7% | 36% |
| LMArena Coding | 1427 | 1211 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| BigCodeBench Instruct | — | 42.8% |
| BigCodeBench Complete | — | 52.5% |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Gemma 2 27B: —
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning DeepSeek-R1 leads
DeepSeek-R1: 18.6 (#278), Gemma 2 27B: 15.3 (#315)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| LiveBench Reasoning | 83.2% | 28.1% |
| LMArena Hard Prompts | 1416 | 1198 |
| LiveBench Data Analysis | 69.8% | 47.9% |
| Epoch Capabilities Index | 141.29 | 122.08 |
| LiveBench | 71.6% | 38.2% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| DTBench | — | 48% |
| LMCA | — | 7.1% |
| ForecastBench | 60 | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Gemma 2 27B: 10.7 (#311)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 1.4% |
| LiveBench Math | 80.7% | 26.5% |
| LMArena Math | 1400 | 1212 |
| MATH Level 5 | 96.6% | 27.9% |
| Omni-MATH | 42.4% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Gemma 2 27B: 19.0 (#280)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| GPQA Diamond | 76.3% | 36.5% |
| Confabulations | 12.7% | 27.1% |
| LMArena Expert | 1394 | 1172 |
| MMLU-Pro | 79.3% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
| MMLU | — | 75.7% |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Gemma 2 27B: 38.6 (#226)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1412 | 1217 |
| LMArena Chinese | 1442 | 1221 |
| LMArena French | 1417 | 1247 |
| LMArena German | 1404 | 1209 |
| LMArena Japanese | 1391 | 1175 |
| LMArena Korean | 1360 | 1174 |
| LMArena Russian | 1423 | 1234 |
| LMArena Spanish | 1411 | 1228 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Gemma 2 27B: 60.5 (#249)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| LiveBench Instruction Following | 80.5% | 58.1% |
| LMArena Instruction Following | 1382 | 1206 |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Gemma 2 27B: 37.3 (#218)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1391 | 1231 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Gemma 2 27B: 44.2 (#225)
| Benchmark | DeepSeek-R1 | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1428 | 1231 |
| LMArena Creative Writing | 1405 | 1241 |
| LMArena Multi-Turn | 1405 | 1224 |
| LiveBench Language | 48.5% | 32.6% |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
Frequently asked questions
Is DeepSeek-R1 better than Gemma 2 27B?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.4 on the Noometry Index.
Which is cheaper, DeepSeek-R1 or Gemma 2 27B?
Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Gemma 2 27B better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-R1 does, with 164K tokens against 8K.
How many benchmarks do DeepSeek-R1 and Gemma 2 27B share?
29 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemma 2 27B has 34.