Model comparison
Claude 3 Haiku vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
StepFunSummary
- 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 37.6 to 9.8.
- 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.
Side by side
| Claude 3 Haiku | Step 3 | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 25.9 | 40.5 |
| Released | 2024-03-07 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Claude 3 Haiku: 26.4 (#325), Step 3: 40.1 (#147)
| 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 Step 3 leads
Claude 3 Haiku: 16.3 (#307), Step 3: 28.4 (#105)
| 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 | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Step 3 leads
Claude 3 Haiku: 9.8 (#319), Step 3: 37.6 (#148)
| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Math | 1188 | 1366 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Step 3 leads
Claude 3 Haiku: 17.3 (#285), Step 3: 36.8 (#164)
| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Expert | 1148 | 1333 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Step 3 leads
Claude 3 Haiku: 23.6 (#128), Step 3: 35.5 (#86)
| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Vision | 950 | 1177 |
| ScienceQA | 72% | — |
Multilingual Step 3 leads
Claude 3 Haiku: 36.0 (#243), Step 3: 46.3 (#159)
| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Non-English | 1178 | 1327 |
| LMArena Chinese | 1155 | 1397 |
| LMArena German | 1174 | 1371 |
| LMArena Korean | 1109 | 1269 |
| LMArena Russian | 1204 | 1331 |
| LMArena Spanish | 1166 | 1371 |
| LMArena French | 1195 | — |
| LMArena Japanese | 1102 | — |
Instruction Following Step 3 leads
Claude 3 Haiku: 61.3 (#247), Step 3: 70.4 (#164)
| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1332 |
Long Context Step 3 leads
Claude 3 Haiku: 36.1 (#237), Step 3: 40.3 (#157)
| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Longer Query | 1190 | 1326 |
Writing & Preference Step 3 leads
Claude 3 Haiku: 29.7 (#291), Step 3: 54.3 (#151)
| Benchmark | Claude 3 Haiku | Step 3 |
|---|---|---|
| LMArena Text | 1195 | 1350 |
| LMArena Creative Writing | 1157 | 1321 |
| LMArena Multi-Turn | 1190 | 1341 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 26.4 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.