Model comparison
DeepSeek LLM 67B vs Gemma 4 26B A4B IT
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
GoogleSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemma 4 26B A4B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 82.2% for Gemma 4 26B A4B IT.
Side by side
| DeepSeek LLM 67B | Gemma 4 26B A4B IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.9 | 43.5 |
| Released | 2023-11-29 | 2026-04-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.0675 |
| Output $ / M tokens | — | $0.23 |
| Results tracked | 15 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 31.9 (#278), Gemma 4 26B A4B IT: 39.0 (#164)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Coding | 1096 | 1447 |
| LMArena WebDev | — | 1359 |
| SciCode | — | 40% |
| WeirdML | — | 35.2% |
| ALE-Bench | — | 927.17 |
Reasoning Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 16.5 (#304), Gemma 4 26B A4B IT: 21.8 (#213)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| Chess Puzzles | 0% | 6% |
| LMArena Hard Prompts | 1070 | 1439 |
| Epoch Capabilities Index | 110.5 | 141.85 |
| CritPt | — | 0% |
| DTBench | — | 74.9% |
| LMCA | — | 29.7% |
Math Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 8.7 (#324), Gemma 4 26B A4B IT: 47.6 (#67)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 82.2% |
| LMArena Math | 1108 | 1470 |
| MATH Level 5 | 6.4% | — |
Knowledge Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 7.0 (#313), Gemma 4 26B A4B IT: 45.7 (#85)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | 24.6% | 73.2% |
| Vectara Hallucination Rate | — | 5.2% |
| LMArena Expert | — | 1447 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Gemma 4 26B A4B IT: 40.6 (#46)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | — | 1260 |
Multilingual Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 29.4 (#267), Gemma 4 26B A4B IT: 53.1 (#71)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1073 | 1421 |
| LMArena Chinese | 1132 | 1495 |
| LMArena French | — | 1460 |
| LMArena Russian | — | 1434 |
| LMArena Spanish | — | 1417 |
Instruction Following Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 55.4 (#277), Gemma 4 26B A4B IT: 74.8 (#82)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1079 | 1420 |
Long Context Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 33.1 (#265), Gemma 4 26B A4B IT: 43.6 (#91)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1092 | 1428 |
Writing & Preference Gemma 4 26B A4B IT leads
DeepSeek LLM 67B: 31.6 (#282), Gemma 4 26B A4B IT: 58.6 (#115)
| Benchmark | DeepSeek LLM 67B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1105 | 1434 |
| LMArena Creative Writing | 1067 | 1402 |
| LMArena Multi-Turn | 1082 | 1441 |
| EQ-Bench Creative Writing | — | 1305 |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Gemma 4 26B A4B IT better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemma 4 26B A4B IT share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemma 4 26B A4B IT has 28.