Claude Haiku 5.5 vs Claude Sonnet 5
Claude Haiku 5.5 leads Claude Sonnet 5 by 5.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 13 and Claude Sonnet 5 wins 4 of 17 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Haiku 5.5 | Claude Sonnet 5 |
|---|---|---|
| Agentic coding | 67 | 57 |
| Long-horizon autonomy | 62 | 65 |
| Knowledge-work agents | 46 | 43 |
| Computer use | 47 | 40 |
| Security & context learning | 55 | 51 |
Shared benchmarks
| Benchmark | Claude Haiku 5.5 | Claude Sonnet 5 |
|---|---|---|
| APEX-Agentsindex | 56.1% | 54.5% |
| Vending-Bench 2index | $3,602 | $6,378 |
| CursorBenchindex | 48.4% | 34.1% |
| Chess Puzzles | 55.0% | 45.0% |
| CritPt | 22.6% | 16.9% |
| DTBench | 95.0% | 92.5% |
| FrontierCode | 46.4% | 42.7% |
| FrontierMath Tier 4 | 46.3% | 29.3% |
| FrontierMath Tiers 1-3 | 75.1% | 65.6% |
| GPQA Diamond | 89.6% | 90.5% |
| LMCA | 51.1% | 50.0% |
| MirrorCode | 78.9% | 63.3% |
| OTIS Mock AIME | 98.9% | 94.7% |
| ProofBench | 89.0% | 77.0% |
| SciCode | 55.0% | 54.3% |
| SimpleBench | 59.2% | 60.6% |
| SimpleQA Verified | 23.8% | 33.7% |
Specs and price
| Claude Haiku 5.5 | Claude Sonnet 5 | |
|---|---|---|
| Agent Index | 57.5 (#18) | 52.4 (#32) |
| Agent $/M | $0.050 | $0.92 |
| Input / output $/M | $0.10 / $0.50 | $2.00 / $10.00 |
| Context | 1M | 1M |
| Released | Oct 7, 2026 | Jun 30, 2026 |
| Weights | Closed | Closed |
| API hosts | 5 | 5 |
Don’t pick one. Route.
Shogo can run Claude Haiku 5.5 and Claude Sonnet 5 side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo