# Mercury 2 vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Mercury 2 scores higher in 1 category and Step 3.5 Flash in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3.5 Flash leads 41.7 to 33.2.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Step 3.5 Flash accepts more context: 256K tokens versus 128K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| Provider | Inception | StepFun |
| Noometry Index | 38.8 | 41.7 |
| Rank | 167 | 116 |
| Context | 128K | 256K |
| Input $/M | $0.25 | $0.10 |
| Output $/M | $0.75 | $0.30 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.2 (#250)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1391 | 1436 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |

## Reasoning

- Mercury 2: 23.0 (#170)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0.8% | — |

## Math

- Mercury 2: —
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| LMArena Math | — | 1408 |

## Knowledge

- Mercury 2: 35.6 (#170)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1358 | 1422 |
| Vectara Hallucination Rate | 12.3% | — |

## Multilingual

- Mercury 2: 46.8 (#153)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1331 | 1386 |
| LMArena Chinese | 1416 | 1448 |
| LMArena Russian | 1303 | 1385 |
| LMArena French | — | 1421 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- Mercury 2: 70.4 (#161)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1328 | 1385 |

## Long Context

- Mercury 2: 40.4 (#149)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1329 | 1402 |

## Writing & Preference

- Mercury 2: 54.0 (#151)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Mercury 2 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1355 | 1403 |
| LMArena Creative Writing | 1289 | 1357 |
| LMArena Multi-Turn | 1358 | 1405 |

## FAQ

### Is Mercury 2 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index.

### Which is cheaper, Mercury 2 or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

### Is Mercury 2 or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 128K.

### How many benchmarks do Mercury 2 and Step 3.5 Flash share?

11 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Step 3.5 Flash has 19.