# Claude 3 Haiku vs Step 3

> Step 3 is the stronger model overall, scoring 39.9 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Step 3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 34.9 to 9.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 34.2% for Claude 3 Haiku and 62.3% for Step 3.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Step 3 |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 25.7 | 39.9 |
| Rank | 333 | 145 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Step 3: 39.5 (#144)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Coding | 1199 | 1367 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Step 3: 27.6 (#102)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 62.3% |
| LMArena Hard Prompts | 1174 | 1355 |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Step 3: 34.9 (#148)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Math | 1188 | 1366 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Step 3: 36.2 (#161)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Expert | 1148 | 1333 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Step 3: 34.9 (#81)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Vision | 950 | 1176 |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Step 3: 46.5 (#154)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Non-English | 1178 | 1327 |
| LMArena Chinese | 1155 | 1396 |
| LMArena German | 1174 | 1371 |
| LMArena Korean | 1108 | 1271 |
| LMArena Russian | 1204 | 1331 |
| LMArena Spanish | 1165 | 1372 |
| LMArena French | 1194 | — |
| LMArena Japanese | 1102 | — |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Step 3: 70.6 (#159)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1332 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Step 3: 40.3 (#152)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Longer Query | 1191 | 1326 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Step 3: 54.5 (#146)

| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Text | 1195 | 1351 |
| LMArena Creative Writing | 1157 | 1322 |
| LMArena Multi-Turn | 1190 | 1340 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Step 3?

Step 3 is the stronger model overall, scoring 39.9 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 39.5 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Step 3 share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Step 3 has 17.