Model comparison
Gemma 4 26B A4B IT vs Step 3
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 40.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
StepFunSummary
- They share 14 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 7 categories and Step 3 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 37.6.
Side by side
| Gemma 4 26B A4B IT | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 43.5 | 40.5 |
| Released | 2026-04-02 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.0675 | — |
| Output $ / M tokens | $0.23 | — |
| Results tracked | 28 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemma 4 26B A4B IT: 39.0 (#164), Step 3: 40.1 (#147)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Coding | 1447 | 1367 |
| LMArena WebDev | 1359 | — |
| SciCode | 40% | — |
| WeirdML | 35.2% | — |
| ALE-Bench | 927.17 | — |
Reasoning Step 3 leads
Gemma 4 26B A4B IT: 21.8 (#213), Step 3: 28.4 (#105)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1439 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 0% | — |
| Chess Puzzles | 6% | — |
| DTBench | 74.9% | — |
| LMCA | 29.7% | — |
| Epoch Capabilities Index | 141.85 | — |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), Step 3: 37.6 (#148)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Math | 1470 | 1366 |
| OTIS Mock AIME 2024-2025 | 82.2% | — |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#85), Step 3: 36.8 (#164)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Expert | 1447 | 1333 |
| GPQA Diamond | 73.2% | — |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 40.6 (#46), Step 3: 35.5 (#86)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Vision | 1260 | 1177 |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.1 (#71), Step 3: 46.3 (#159)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Non-English | 1421 | 1327 |
| LMArena Chinese | 1495 | 1397 |
| LMArena Russian | 1434 | 1331 |
| LMArena Spanish | 1417 | 1371 |
| LMArena French | 1460 | — |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 74.8 (#82), Step 3: 70.4 (#164)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1332 |
Long Context Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 43.6 (#91), Step 3: 40.3 (#157)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Longer Query | 1428 | 1326 |
Writing & Preference Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 58.6 (#115), Step 3: 54.3 (#151)
| Benchmark | Gemma 4 26B A4B IT | Step 3 |
|---|---|---|
| LMArena Text | 1434 | 1350 |
| LMArena Creative Writing | 1402 | 1321 |
| LMArena Multi-Turn | 1441 | 1341 |
| EQ-Bench Creative Writing | 1305 | — |
Frequently asked questions
Is Gemma 4 26B A4B IT better than Step 3?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 40.5 on the Noometry Index.
Is Gemma 4 26B A4B IT or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 39.0 in the Noometry coding category.
How many benchmarks do Gemma 4 26B A4B IT and Step 3 share?
14 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Step 3 has 17.