Model comparison
DeepSeek-R1 vs Gemma 2 2b IT
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 33.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
GoogleSummary
- They share 17 benchmarks with published results for both. DeepSeek-R1 scores higher in 7 categories and Gemma 2 2b IT in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1 leads 61.4 to 36.5.
- Gemma 2 2b IT has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Gemma 2 2b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.3 | 33.1 |
| Released | 2025-01-20 | — |
| Weights | Proprietary | Open |
| Context window | 164K | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $2.15 | — |
| Results tracked | 52 | 17 |
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 2b IT: 32.3 (#273)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Coding | 1427 | 1112 |
| 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), Gemma 2 2b IT: —
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Gemma 2 2b IT leads
DeepSeek-R1: 18.6 (#278), Gemma 2 2b IT: 21.4 (#224)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1113 |
| 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% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.29 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Gemma 2 2b IT: 32.6 (#212)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Math | 1400 | 1135 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Gemma 2 2b IT: 29.9 (#231)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Expert | 1394 | 1096 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Gemma 2 2b IT: 32.3 (#257)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Non-English | 1412 | 1121 |
| LMArena Chinese | 1442 | 1132 |
| LMArena French | 1417 | 1157 |
| LMArena German | 1404 | 1114 |
| LMArena Japanese | 1391 | 1083 |
| LMArena Korean | 1360 | 1055 |
| LMArena Russian | 1423 | 1118 |
| LMArena Spanish | 1411 | 1140 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Gemma 2 2b IT: 57.8 (#263)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Instruction Following | 1382 | 1118 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Gemma 2 2b IT: 34.3 (#250)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Longer Query | 1391 | 1130 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Gemma 2 2b IT: 36.5 (#263)
| Benchmark | DeepSeek-R1 | Gemma 2 2b IT |
|---|---|---|
| LMArena Text | 1428 | 1156 |
| LMArena Creative Writing | 1405 | 1147 |
| LMArena Multi-Turn | 1405 | 1118 |
| 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 Gemma 2 2b IT?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 33.1 on the Noometry Index.
Is DeepSeek-R1 or Gemma 2 2b IT better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 32.3 in the Noometry coding category.
How many benchmarks do DeepSeek-R1 and Gemma 2 2b IT share?
17 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemma 2 2b IT has 17.