# Mercury 2.5 vs Step 3

> Step 3 has enough public results to be ranked (#145); Mercury 2.5 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/mercury-2-5-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Step 3 leads 34.9 to 22.4.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2.5 | Step 3 |
|---|---|---|
| Provider | Inception | StepFun |
| Noometry Index | 30.2 | 39.9 |
| Rank | — | 145 |
| Context | 260K | — |
| Input $/M | $0.04 | — |
| Output $/M | $0.15 | — |
| Weights | Proprietary | Open |

## Coding

- Mercury 2.5: —
- Step 3: 39.5 (#144)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |
| ALE-Bench | 301.65 | — |

## Reasoning

- Mercury 2.5: —
- Step 3: 27.6 (#102)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| LMArena Hard Prompts | — | 1355 |

## Math

- Mercury 2.5: 22.4
- Step 3: 34.9 (#148)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| ProofBench | 3% | — |
| LMArena Math | — | 1366 |

## Knowledge

- Mercury 2.5: —
- Step 3: 36.2 (#161)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |

## Multimodal

- Mercury 2.5: —
- Step 3: 34.9 (#81)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |

## Multilingual

- Mercury 2.5: —
- Step 3: 46.5 (#154)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |

## Instruction Following

- Mercury 2.5: —
- Step 3: 70.6 (#159)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |

## Long Context

- Mercury 2.5: —
- Step 3: 40.3 (#152)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |

## Writing & Preference

- Mercury 2.5: —
- Step 3: 54.5 (#146)

| Benchmark | Mercury 2.5 | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |

## FAQ

### Is Mercury 2.5 better than Step 3?

Step 3 has enough public results to be ranked (#145); Mercury 2.5 does not yet, so treat this comparison as directional.

### How many benchmarks do Mercury 2.5 and Step 3 share?

0 benchmarks have published results for both models. Mercury 2.5 has 2 scored results on Noometry and Step 3 has 17.