Gemma 4 26B A4B vs Step 5 Preview
Updated October 21, 2026. 36 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 22.8 for Gemma 4 26B A4B.
Pick Gemma 4 26B A4B when output tokens cost 10.6x less, or when what matters is LMArena Vision: homework or LMArena Text: math, where it leads.
- Shared results
- 36
- Gemma 4 26B A4B only
- 18
- Step 5 Preview only
- 25
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Step 5 Preview
Step 5 Preview scores 71.4 against 22.8.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Step 5 Preview
Step 5 Preview leads, 43.7 against 16.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemma 4 26B A4B has a AA Agentic Index result, 2.9.
Directional only
Long documents
Listed context window
Step 5 Preview
Step 5 Preview takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 26B A4B
Gemma 4 26B A4B $0.0002, Step 5 Preview $0.0024 per turn.
List prices
At a glance
- Coding index
- Gemma 4 26B A4B 22.8 from 1 benchmark, Step 5 Preview 71.4 from 2 benchmarks.
- Widest category
- Intelligence, 27.0 points apart on average over 1 shared benchmark.
- Widest single gap
- LMArena WebDev: React: Gemma 4 26B A4B 1351 against Step 5 Preview 1583, 38.7 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 26B A4B $0.255 against Step 5 Preview $2.70 per million output tokens, 10.6x apart.
- Context window
- Gemma 4 26B A4B takes 262K tokens, Step 5 Preview 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemma 4 26B A4B | Bars | Step 5 Preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 1 | 5 | ||
| Math | 2 | 0 | ||
| Knowledge | 1 | 3 | ||
| General | 3 | 14 | ||
| All shared boards | 7 | 29 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index06
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 85.6% | Only Step 5 Preview measured |
| LMArena WebDev | 1360 | 1567 | Step 5 Preview |
| AA Coding Index | 39.3 | Not measured | Only Gemma 4 26B A4B measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 31.8% | Only Step 5 Preview measured |
| Vibe Code Bench (Vals AI) | Not measured | 70.4% | Only Step 5 Preview measured |
| Code migration (Vals AI) | Not measured | 39.0% | Only Step 5 Preview measured |
| IOI (Vals AI) | Not measured | 38.1% | Only Step 5 Preview measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 40.8% | Only Step 5 Preview measured |
| SciCode | 40.0% | 58.9% | Step 5 Preview |
| Terminal-Bench Hard (Artificial Analysis run) | 25.0% | Not measured | Only Gemma 4 26B A4B measured |
| WeirdML | 35.2% | Not measured | Only Gemma 4 26B A4B measured |
| ALE-Bench | 927.2 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: coding | 1446 | 1485 | Step 5 Preview |
| LMArena Text: software and IT | 1454 | 1473 | Step 5 Preview |
| LMArena WebDev: React | 1351 | 1583 | Step 5 Preview |
| LMArena WebDev: HTML | 1362 | 1556 | Step 5 Preview |
| LMArena WebDev: from an image | Not measured | 1550 | Only Step 5 Preview measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.7 | 43.7 | Step 5 Preview |
| Epoch Capabilities Index | 141.9 | Not measured | Only Gemma 4 26B A4B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 2.9 | Not measured | Only Gemma 4 26B A4B measured |
| LiveBench research | Not measured | 72.8% | Only Step 5 Preview measured |
| LiveBench browser | Not measured | 24.0% | Only Step 5 Preview measured |
| LiveBench long agentic | Not measured | 27.5% | Only Step 5 Preview measured |
| SREBench (Vals AI) | Not measured | 0.4% | Only Step 5 Preview measured |
| Finance Agent (Vals AI) | Not measured | 50.7% | Only Step 5 Preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 27.3% | Only Step 5 Preview measured |
| Legal Research Bench (Vals AI) | Not measured | 40.4% | Only Step 5 Preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 57.1% | Only Step 5 Preview measured |
| BioMysteryBench (Vals AI) | Not measured | 67.4% | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 2.9% | Only Step 5 Preview measured |
| Vals Science Index | Not measured | 29.6% | Only Step 5 Preview measured |
| τ²-Bench Telecom | 43.6% | Not measured | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 83.8% | Only Step 5 Preview measured |
| MysteryMechanism (Vals AI) | Not measured | 18.5% | Only Step 5 Preview measured |
| GPQA Diamond (Artificial Analysis run) | 79.2% | Not measured | Only Gemma 4 26B A4B measured |
| Humanity's Last Exam (Artificial Analysis run) | 19.3% | 46.5% | Step 5 Preview |
| GPQA Diamond (Epoch AI run) | 73.2% | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: hard prompts | 1438 | 1461 | Step 5 Preview |
| LMArena Text: expert | 1447 | 1485 | Step 5 Preview |
| LMArena Text: hard prompts in English | 1448 | 1454 | Step 5 Preview |
| LMArena Vision: diagrams | 1264 | 1308 | Step 5 Preview |
| LMArena Vision: homework | 1293 | 1265 | Gemma 4 26B A4B |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 82.2% | Not measured | Only Gemma 4 26B A4B measured |
| ProofBench | Not measured | 42.0% | Only Step 5 Preview measured |
| LMArena Text: math | 1470 | 1458 | Gemma 4 26B A4B |
| LMArena Text: mathematical work | 1475 | 1460 | Gemma 4 26B A4B |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| LMArena Text: science | 1446 | 1454 | Step 5 Preview |
| LMArena Text: medicine and healthcare | 1428 | 1439 | Step 5 Preview |
| LMArena Text: legal and government | 1457 | 1437 | Gemma 4 26B A4B |
| LMArena Text: business and finance | 1429 | 1435 | Step 5 Preview |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench design | Not measured | 76.9% | Only Step 5 Preview measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index314
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 63.5% | Only Step 5 Preview measured |
| Public Benefits Bench (Vals AI) | Not measured | 58.1% | Only Step 5 Preview measured |
| IFBench | 72.4% | Not measured | Only Gemma 4 26B A4B measured |
| Long context reasoning (AA-LCR) | 65.7% | 88.3% | Step 5 Preview |
| DTBench | 74.9% | Not measured | Only Gemma 4 26B A4B measured |
| LMCA | 29.7% | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text | 1434 | 1440 | Step 5 Preview |
| LMArena Text: instruction following | 1420 | 1438 | Step 5 Preview |
| LMArena Text: creative writing | 1400 | 1409 | Step 5 Preview |
| LMArena Vision | 1260 | 1265 | Step 5 Preview |
| LMArena Text: English | 1444 | 1447 | Step 5 Preview |
| LMArena Text: non-English | 1421 | 1428 | Step 5 Preview |
| LMArena Text: Chinese | 1495 | 1500 | Step 5 Preview |
| LMArena Text: Japanese | Not measured | 1383 | Only Step 5 Preview measured |
| LMArena Text: French | 1460 | 1438 | Gemma 4 26B A4B |
| LMArena Text: Spanish | 1415 | 1441 | Step 5 Preview |
| LMArena Text: Russian | 1434 | 1433 | Gemma 4 26B A4B |
| LMArena Text: multi-turn | 1441 | 1437 | Gemma 4 26B A4B |
| LMArena Text: longer queries | 1427 | 1449 | Step 5 Preview |
| LMArena Text: writing and language | 1405 | 1425 | Step 5 Preview |
| LMArena Text: entertainment and media | 1403 | 1412 | Step 5 Preview |
| LMArena Vision: English | 1256 | 1290 | Step 5 Preview |
| LMArena Vision: Chinese | 1312 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: reading text | 1268 | 1282 | Step 5 Preview |
| LMArena Vision: humor | 1272 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: captioning | 1297 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: recognizing things | 1191 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: creative writing | 1256 | Not measured | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 26B A4B | Step 5 Preview | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 4 26B A4B costs less
Repository review
50K input + 3K output tokens
Gemma 4 26B A4B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 26B A4B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemma 4 26B A4B | StepFun Step 5 Preview |
|---|---|---|
| Maker | StepFun | |
| Weights | Open weights | Open weights |
| Released | April 3, 2026 | October 8, 2026 |
| Context window | 262K | 1.05M |
| Input $/Mtok | $0.0765 | $1.00 |
| Output $/Mtok | $0.255 | $2.70 |
| Coding index | 22.8 | 71.4 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 26B A4B better than Step 5 Preview for coding?
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 22.8 for Gemma 4 26B A4B. Pick Gemma 4 26B A4B when output tokens cost 10.6x less, or when what matters is LMArena Vision: homework or LMArena Text: math, where it leads.
Which is cheaper, Gemma 4 26B A4B or Step 5 Preview?
Gemma 4 26B A4B costs $0.0765 per million input tokens and $0.255 per million output tokens; Step 5 Preview costs $1.00 and $2.70. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 4 26B A4B or Step 5 Preview?
Step 5 Preview, with 1.05M tokens against 262K.
How many benchmarks is the Gemma 4 26B A4B vs Step 5 Preview comparison based on?
36 benchmarks have a result for both models as of October 21, 2026. Gemma 4 26B A4B's coding index rests on 1 independent benchmark and Step 5 Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.