Model comparison
Claude Haiku 4.5 vs Step 1o Turbo 202506
Claude Haiku 4.5 and Step 1o Turbo 202506 score almost the same on the Noometry Index (39.5 vs 39.7), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
StepFunSummary
- They share 13 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Step 1o Turbo 202506 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 1o Turbo 202506 leads 26.8 to 15.1.
Side by side
| Claude Haiku 4.5 | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 39.5 | 39.7 |
| Released | 2025-10-15 | — |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 14 |
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 1o Turbo 202506: 39.2 (#160)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1453 | 1339 |
| 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 1o Turbo 202506: —
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| 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 1o Turbo 202506 leads
Claude Haiku 4.5: 15.1 (#320), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1335 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| 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 1o Turbo 202506: 36.6 (#164)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1396 | 1318 |
| 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 Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1442 | 1308 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Step 1o Turbo 202506 leads
Claude Haiku 4.5: 26.8 (#118), Step 1o Turbo 202506: 36.1 (#80)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | — | 1186 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 1377 | 1313 |
| LMArena Chinese | 1417 | 1380 |
| LMArena German | 1375 | 1314 |
| LMArena Russian | 1381 | 1327 |
| LMArena French | 1408 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1310 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1427 | 1348 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | Claude Haiku 4.5 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1396 | 1336 |
| LMArena Creative Writing | 1372 | 1307 |
| LMArena Multi-Turn | 1409 | 1340 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Step 1o Turbo 202506?
Claude Haiku 4.5 and Step 1o Turbo 202506 score almost the same on the Noometry Index (39.5 vs 39.7), so choose on price, context window or the category you care about most.
Is Claude Haiku 4.5 or Step 1o Turbo 202506 better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 39.2 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Step 1o Turbo 202506 share?
13 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Step 1o Turbo 202506 has 14.