Model comparison
DeepSeek-R1-Distill-Qwen-32B vs Gemma 4 26B A4B IT
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 35.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeek
GoogleSummary
- They share 4 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-32B scores higher in 0 categories and Gemma 4 26B A4B IT in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 4 26B A4B IT leads 74.8 to 61.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for DeepSeek-R1-Distill-Qwen-32B and 82.2% for Gemma 4 26B A4B IT.
Side by side
| DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.5 | 43.5 |
| Released | 2025-01-20 | 2026-04-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.0675 |
| Output $ / M tokens | — | $0.23 |
| Results tracked | 14 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 26B A4B IT leads
DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212), Gemma 4 26B A4B IT: 39.0 (#164)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena WebDev | — | 1359 |
| SciCode | — | 40% |
| WeirdML | — | 35.2% |
| BigCodeBench Instruct | 43.9% | — |
| LiveBench Coding | 33.7% | — |
| LMArena Coding | — | 1447 |
| BigCodeBench Complete | 54.9% | — |
| ALE-Bench | — | 927.17 |
Agentic & Tool Use Not comparable
DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94), Gemma 4 26B A4B IT: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| BALROG | 19.5% | — |
Reasoning Gemma 4 26B A4B IT leads
DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284), Gemma 4 26B A4B IT: 21.8 (#213)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| Chess Puzzles | 1% | 6% |
| Epoch Capabilities Index | 137.44 | 141.85 |
| CritPt | — | 0% |
| LiveBench Reasoning | 52.3% | — |
| LMArena Hard Prompts | — | 1439 |
| DTBench | — | 74.9% |
| LiveBench Data Analysis | 45.4% | — |
| LMCA | — | 29.7% |
| LiveBench | 45.5% | — |
Math Gemma 4 26B A4B IT leads
DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194), Gemma 4 26B A4B IT: 47.6 (#67)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 82.2% |
| LiveBench Math | 59.4% | — |
| LMArena Math | — | 1470 |
Knowledge Gemma 4 26B A4B IT leads
DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182), Gemma 4 26B A4B IT: 45.7 (#85)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | 64.1% | 73.2% |
| Vectara Hallucination Rate | — | 5.2% |
| LMArena Expert | — | 1447 |
Multimodal Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Gemma 4 26B A4B IT: 40.6 (#46)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | — | 1260 |
Multilingual Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Gemma 4 26B A4B IT: 53.1 (#71)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | — | 1421 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1460 |
| LMArena Russian | — | 1434 |
| LMArena Spanish | — | 1417 |
Instruction Following Gemma 4 26B A4B IT leads
DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243), Gemma 4 26B A4B IT: 74.8 (#82)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| LiveBench Instruction Following | 55.7% | — |
| LMArena Instruction Following | — | 1420 |
Long Context Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Gemma 4 26B A4B IT: 43.6 (#91)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | — | 1428 |
Writing & Preference Gemma 4 26B A4B IT leads
DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188), Gemma 4 26B A4B IT: 58.6 (#115)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | — | 1434 |
| LMArena Creative Writing | — | 1402 |
| EQ-Bench Creative Writing | — | 1305 |
| LMArena Multi-Turn | — | 1441 |
| LiveBench Language | 26.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-32B better than Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 35.5 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-32B or Gemma 4 26B A4B IT better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 36.1 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-32B and Gemma 4 26B A4B IT share?
4 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-32B has 14 scored results on Noometry and Gemma 4 26B A4B IT has 28.