Model comparison
Claude Haiku 4.5 vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 39.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
StepFunSummary
- They share 18 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 3 categories and Step 3.5 Flash in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3.5 Flash leads 22.2 to 15.1.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Step 3.5 Flash accepts more context: 256K tokens versus 200K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Step 3.5 Flash | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 39.5 | 42.3 |
| Released | 2025-10-15 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | 200K | 256K |
| Max output | 64K | 256K |
| Input $ / M tokens | $1 | $0.10 |
| Output $ / M tokens | $5 | $0.30 |
| Results tracked | 53 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1453 | 1436 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Step 3.5 Flash: —
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Step 3.5 Flash leads
Claude Haiku 4.5: 15.1 (#320), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 14.3% | 28.4% |
| LMArena Hard Prompts | 1420 | 1411 |
| ARC-AGI-2 | 4% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1396 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Step 3.5 Flash leads
Claude Haiku 4.5: 37.7 (#153), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1442 | 1421 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Step 3.5 Flash: —
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Too close to call
Claude Haiku 4.5: 49.9 (#129), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1377 | 1385 |
| LMArena Chinese | 1417 | 1447 |
| LMArena French | 1408 | 1421 |
| LMArena German | 1375 | 1405 |
| LMArena Japanese | 1339 | 1354 |
| LMArena Korean | 1347 | 1352 |
| LMArena Russian | 1381 | 1385 |
| LMArena Spanish | 1420 | 1419 |
Instruction Following Step 3.5 Flash leads
Claude Haiku 4.5: 71.4 (#149), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1414 | 1385 |
| IFEval | 80.1% | — |
Long Context Too close to call
Claude Haiku 4.5: 43.6 (#92), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1427 | 1402 |
Writing & Preference Too close to call
Claude Haiku 4.5: 57.9 (#123), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Claude Haiku 4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1396 | 1403 |
| LMArena Creative Writing | 1372 | 1357 |
| LMArena Multi-Turn | 1409 | 1405 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 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; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Step 3.5 Flash better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Step 3.5 Flash share?
18 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Step 3.5 Flash has 19.