Model comparison
Gemma 3 27B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 30.8 on the Noometry Index. Gemma 3 27B costs 1.5× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Google
StepFunSummary
- They share 17 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3.5 Flash leads 42.4 to 22.5.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
- Step 3.5 Flash accepts more context: 256K tokens versus 131K.
Side by side
| Gemma 3 27B | Step 3.5 Flash | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 30.8 | 42.3 |
| Released | 2025-03-11 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 8K | 256K |
| Input $ / M tokens | $0.08 | $0.10 |
| Output $ / M tokens | $0.16 | $0.30 |
| Results tracked | 43 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Gemma 3 27B: 22.5 (#334), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1322 | 1436 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Step 3.5 Flash: —
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Step 3.5 Flash leads
Gemma 3 27B: 16.7 (#301), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1411 |
| Kagi LLM Benchmark | 40.4% | — |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Step 3.5 Flash leads
Gemma 3 27B: 25.9 (#265), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1312 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Step 3.5 Flash leads
Gemma 3 27B: 25.5 (#261), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1304 | 1421 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Step 3.5 Flash: —
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Step 3.5 Flash leads
Gemma 3 27B: 46.9 (#155), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1334 | 1385 |
| LMArena Chinese | 1346 | 1447 |
| LMArena French | 1368 | 1421 |
| LMArena German | 1362 | 1405 |
| LMArena Japanese | 1287 | 1354 |
| LMArena Korean | 1308 | 1352 |
| LMArena Russian | 1349 | 1385 |
| LMArena Spanish | 1349 | 1419 |
Instruction Following Step 3.5 Flash leads
Gemma 3 27B: 70.6 (#160), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1321 | 1385 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Step 3.5 Flash leads
Gemma 3 27B: 27.6 (#293), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1333 | 1402 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Step 3.5 Flash leads
Gemma 3 27B: 52.5 (#168), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Gemma 3 27B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1358 | 1403 |
| LMArena Creative Writing | 1346 | 1357 |
| LMArena Multi-Turn | 1345 | 1405 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 30.8 on the Noometry Index. Gemma 3 27B costs 1.5× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or Step 3.5 Flash?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.
Is Gemma 3 27B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 131K.
How many benchmarks do Gemma 3 27B and Step 3.5 Flash share?
17 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Step 3.5 Flash has 19.