Model comparison
Gemini 2.5 Pro vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
StepFunSummary
- They share 17 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 5 categories and Step 5 Preview in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 44.5.
- The biggest single-benchmark swing is CritPt: 2% for Gemini 2.5 Pro and 20.9% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1.02M.
Side by side
| Gemini 2.5 Pro | Step 5 Preview | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 45.0 | 47.9 |
| Released | 2025-03-25 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 66K | 66K |
| Input $ / M tokens | $1.25 | $1 |
| Output $ / M tokens | $10 | $2.70 |
| Results tracked | 78 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Gemini 2.5 Pro: 42.4 (#101), Step 5 Preview: 51.8 (#36)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1227 | 1564 |
| SciCode | 42.8% | 58.9% |
| LMArena Coding | 1452 | 1480 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Pro: 29.2 (#88), Step 5 Preview: —
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Step 5 Preview leads
Gemini 2.5 Pro: 28.8 (#99), Step 5 Preview: 40.0 (#57)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| CritPt | 2% | 20.9% |
| LMArena Hard Prompts | 1455 | 1465 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 41% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| DTBench | 82.4% | — |
| LiveBench Data Analysis | 79.9% | — |
| LMCA | 34.8% | — |
| Epoch Capabilities Index | 145.32 | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |
Math Step 5 Preview leads
Gemini 2.5 Pro: 32.5 (#213), Step 5 Preview: 46.1 (#72)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena Math | 1450 | 1470 |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| ProofBench | — | 42% |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 56.0 (#46), Step 5 Preview: 41.2 (#112)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1452 | 1470 |
| GPQA Diamond | 85.3% | — |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |
Multimodal Gemini 2.5 Pro leads
Gemini 2.5 Pro: 45.2 (#18), Step 5 Preview: 41.0 (#41)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1263 | 1267 |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.3 (#31), Step 5 Preview: 53.8 (#54)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1451 | 1432 |
| LMArena Chinese | 1507 | 1519 |
| LMArena Russian | 1461 | 1436 |
| LMArena Spanish | 1473 | 1439 |
| LMArena French | 1472 | — |
| LMArena German | 1487 | — |
| LMArena Japanese | 1461 | — |
| LMArena Korean | 1434 | — |
Instruction Following Too close to call
Gemini 2.5 Pro: 75.0 (#75), Step 5 Preview: 76.0 (#50)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1437 | 1444 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), Step 5 Preview: 44.5 (#64)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1449 | 1455 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Too close to call
Gemini 2.5 Pro: 63.7 (#62), Step 5 Preview: 62.8 (#71)
| Benchmark | Gemini 2.5 Pro | Step 5 Preview |
|---|---|---|
| LMArena Text | 1458 | 1442 |
| LMArena Creative Writing | 1454 | 1410 |
| LMArena Multi-Turn | 1453 | 1447 |
| Short-Story Creative Writing | 83.8% | — |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.0 on the Noometry Index.
Which is cheaper, Gemini 2.5 Pro or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Is Gemini 2.5 Pro or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 1.02M.
How many benchmarks do Gemini 2.5 Pro and Step 5 Preview share?
17 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Step 5 Preview has 18.