Model comparison
Claude 3 Haiku vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 25.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 40.6 to 9.2.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Step 3.5 Flash | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 25.7 | 41.7 |
| Released | 2024-03-07 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 37 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Claude 3 Haiku: 26.1 (#320), Step 3.5 Flash: 41.7 (#106)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1199 | 1436 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Step 3.5 Flash leads
Claude 3 Haiku: 15.7 (#303), Step 3.5 Flash: 21.2 (#202)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1411 |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 28.4% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Step 3.5 Flash leads
Claude 3 Haiku: 9.2 (#313), Step 3.5 Flash: 40.6 (#77)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1188 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Step 3.5 Flash leads
Claude 3 Haiku: 17.3 (#280), Step 3.5 Flash: 39.0 (#127)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1148 | 1422 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), Step 3.5 Flash: —
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Step 3.5 Flash leads
Claude 3 Haiku: 36.1 (#238), Step 3.5 Flash: 50.7 (#115)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1178 | 1386 |
| LMArena Chinese | 1155 | 1448 |
| LMArena French | 1194 | 1421 |
| LMArena German | 1174 | 1404 |
| LMArena Japanese | 1102 | 1353 |
| LMArena Korean | 1108 | 1350 |
| LMArena Russian | 1204 | 1385 |
| LMArena Spanish | 1165 | 1419 |
Instruction Following Step 3.5 Flash leads
Claude 3 Haiku: 61.5 (#242), Step 3.5 Flash: 73.3 (#119)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1174 | 1385 |
Long Context Step 3.5 Flash leads
Claude 3 Haiku: 36.1 (#232), Step 3.5 Flash: 42.8 (#112)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1191 | 1402 |
Writing & Preference Step 3.5 Flash leads
Claude 3 Haiku: 29.8 (#286), Step 3.5 Flash: 59.0 (#108)
| Benchmark | Claude 3 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1195 | 1403 |
| LMArena Creative Writing | 1157 | 1357 |
| LMArena Multi-Turn | 1190 | 1405 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Step 3.5 Flash share?
17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Step 3.5 Flash has 19.