Model comparison
DeepSeek-R1 vs Gemma 4 26B A4B IT
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 42.3 on the Noometry Index.
Last verified . 23 shared benchmarks.
DeepSeek
GoogleSummary
- They share 23 benchmarks with published results for both. DeepSeek-R1 scores higher in 3 categories and Gemma 4 26B A4B IT in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-R1 leads 46.3 to 39.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 82.2% for Gemma 4 26B A4B IT.
- Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- Gemma 4 26B A4B IT accepts more context: 262K tokens versus 164K.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Gemma 4 26B A4B IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.3 | 43.5 |
| Released | 2025-01-20 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 164K | 262K |
| Max output | 64K | 33K |
| Input $ / M tokens | $0.50 | $0.0675 |
| Output $ / M tokens | $2.15 | $0.23 |
| Results tracked | 52 | 28 |
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 4 26B A4B IT: 39.0 (#164)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| SciCode | 35.7% | 40% |
| WeirdML | 41.6% | 35.2% |
| LMArena Coding | 1427 | 1447 |
| ALE-Bench | 804.12 | 927.17 |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1359 |
| LiveBench Coding | 66.7% | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Gemma 4 26B A4B IT: —
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Gemma 4 26B A4B IT leads
DeepSeek-R1: 18.6 (#278), Gemma 4 26B A4B IT: 21.8 (#213)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1416 | 1439 |
| Epoch Capabilities Index | 141.29 | 141.85 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 83.2% | — |
| DTBench | — | 74.9% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 29.7% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Gemma 4 26B A4B IT leads
DeepSeek-R1: 43.8 (#79), Gemma 4 26B A4B IT: 47.6 (#67)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 82.2% |
| LMArena Math | 1400 | 1470 |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge Gemma 4 26B A4B IT leads
DeepSeek-R1: 44.5 (#87), Gemma 4 26B A4B IT: 45.7 (#85)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | 76.3% | 73.2% |
| Vectara Hallucination Rate | 11.3% | 5.2% |
| LMArena Expert | 1394 | 1447 |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, Gemma 4 26B A4B IT: 40.6 (#46)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | — | 1260 |
Multilingual Too close to call
DeepSeek-R1: 52.4 (#85), Gemma 4 26B A4B IT: 53.1 (#71)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1412 | 1421 |
| LMArena Chinese | 1442 | 1495 |
| LMArena French | 1417 | 1460 |
| LMArena Russian | 1423 | 1434 |
| LMArena Spanish | 1411 | 1417 |
| LMArena German | 1404 | — |
| LMArena Japanese | 1391 | — |
| LMArena Korean | 1360 | — |
Instruction Following Gemma 4 26B A4B IT leads
DeepSeek-R1: 72.0 (#143), Gemma 4 26B A4B IT: 74.8 (#82)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1382 | 1420 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Gemma 4 26B A4B IT: 43.6 (#91)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1391 | 1428 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Gemma 4 26B A4B IT: 58.6 (#115)
| Benchmark | DeepSeek-R1 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1428 | 1434 |
| LMArena Creative Writing | 1405 | 1402 |
| EQ-Bench Creative Writing | 1500 | 1305 |
| LMArena Multi-Turn | 1405 | 1441 |
| Short-Story Creative Writing | 83% | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 42.3 on the Noometry Index.
Which is cheaper, DeepSeek-R1 or Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Gemma 4 26B A4B IT better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 39.0 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 26B A4B IT does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-R1 and Gemma 4 26B A4B IT share?
23 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemma 4 26B A4B IT has 28.