Model comparison
Gemma 3 27B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
StepFunSummary
- They share 12 benchmarks with published results for both. Gemma 3 27B scores higher in 3 categories and Step 2 16k Exp 202412 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 2 16k Exp 202412 leads 38.5 to 22.5.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 27B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 30.8 | 39.2 |
| 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 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Gemma 3 27B: 22.5 (#334), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1322 | 1316 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Step 2 16k Exp 202412: —
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Step 2 16k Exp 202412 leads
Gemma 3 27B: 16.7 (#301), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1299 |
| 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 2 16k Exp 202412 leads
Gemma 3 27B: 25.9 (#265), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1312 | 1304 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Step 2 16k Exp 202412 leads
Gemma 3 27B: 25.5 (#261), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1304 | 1279 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Step 2 16k Exp 202412: —
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1334 | 1290 |
| LMArena Chinese | 1346 | 1331 |
| LMArena Russian | 1349 | 1324 |
| LMArena French | 1368 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1287 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Step 2 16k Exp 202412 leads
Gemma 3 27B: 27.6 (#293), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1333 | 1307 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Too close to call
Gemma 3 27B: 52.5 (#168), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Gemma 3 27B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1358 | 1321 |
| LMArena Creative Writing | 1346 | 1328 |
| LMArena Multi-Turn | 1345 | 1292 |
| 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 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 30.8 on the Noometry Index.
Is Gemma 3 27B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Step 2 16k Exp 202412 has 12.