Model comparison
Gemma 3 27B vs Step 1o Turbo 202506
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 30.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
StepFunSummary
- They share 14 benchmarks with published results for both. Gemma 3 27B scores higher in 2 categories and Step 1o Turbo 202506 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 1o Turbo 202506 leads 39.2 to 22.5.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 27B | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 30.8 | 39.7 |
| Released | 2025-03-11 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 1o Turbo 202506 leads
Gemma 3 27B: 22.5 (#334), Step 1o Turbo 202506: 39.2 (#160)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1322 | 1339 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Step 1o Turbo 202506: —
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Step 1o Turbo 202506 leads
Gemma 3 27B: 16.7 (#301), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1335 |
| Kagi LLM Benchmark | 40.4% | — |
| 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 1o Turbo 202506 leads
Gemma 3 27B: 25.9 (#265), Step 1o Turbo 202506: 36.6 (#164)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1312 | 1318 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Step 1o Turbo 202506 leads
Gemma 3 27B: 25.5 (#261), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1304 | 1308 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Step 1o Turbo 202506 leads
Gemma 3 27B: 32.6 (#100), Step 1o Turbo 202506: 36.1 (#80)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | 1164 | 1186 |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 1334 | 1313 |
| LMArena Chinese | 1346 | 1380 |
| LMArena German | 1362 | 1314 |
| LMArena Russian | 1349 | 1327 |
| LMArena French | 1368 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1310 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Step 1o Turbo 202506 leads
Gemma 3 27B: 27.6 (#293), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1333 | 1348 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Too close to call
Gemma 3 27B: 52.5 (#168), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | Gemma 3 27B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1358 | 1336 |
| LMArena Creative Writing | 1346 | 1307 |
| LMArena Multi-Turn | 1345 | 1340 |
| 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 1o Turbo 202506?
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 30.8 on the Noometry Index.
Is Gemma 3 27B or Step 1o Turbo 202506 better for coding?
Step 1o Turbo 202506 scores higher on coding benchmarks: 39.2 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Step 1o Turbo 202506 share?
14 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Step 1o Turbo 202506 has 14.