Model comparison
Claude 3.5 Haiku vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 29.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude 3.5 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 42.6 to 14.7.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Step 3.5 Flash | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 29.2 | 42.3 |
| Released | 2024-10-22 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 49 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Claude 3.5 Haiku: 32.9 (#265), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1286 | 1436 |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), Step 3.5 Flash: —
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Step 3.5 Flash leads
Claude 3.5 Haiku: 17.7 (#290), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |
Math Step 3.5 Flash leads
Claude 3.5 Haiku: 14.7 (#300), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1244 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Step 3.5 Flash leads
Claude 3.5 Haiku: 18.7 (#281), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1208 | 1421 |
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), Step 3.5 Flash: —
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Step 3.5 Flash leads
Claude 3.5 Haiku: 40.0 (#218), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1238 | 1385 |
| LMArena Chinese | 1229 | 1447 |
| LMArena French | 1264 | 1421 |
| LMArena German | 1237 | 1405 |
| LMArena Japanese | 1175 | 1354 |
| LMArena Korean | 1173 | 1352 |
| LMArena Russian | 1253 | 1385 |
| LMArena Spanish | 1261 | 1419 |
Instruction Following Step 3.5 Flash leads
Claude 3.5 Haiku: 62.9 (#234), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1241 | 1385 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Step 3.5 Flash leads
Claude 3.5 Haiku: 38.3 (#200), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1261 | 1402 |
Writing & Preference Step 3.5 Flash leads
Claude 3.5 Haiku: 42.7 (#234), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Claude 3.5 Haiku | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1255 | 1403 |
| LMArena Creative Writing | 1233 | 1357 |
| LMArena Multi-Turn | 1265 | 1405 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Step 3.5 Flash share?
17 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Step 3.5 Flash has 19.