Claude Sonnet 5 vs Claude Sonnet 5.5
Claude Sonnet 5.5 leads Claude Sonnet 5 by 16.6 points on the Shogo Agent Index. Claude Sonnet 5 wins 0 and Claude Sonnet 5.5 wins 18 of 18 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| Agentic coding | 57 | 79 |
| Long-horizon autonomy | 65 | 75 |
| Knowledge-work agents | 43 | 57 |
| Computer use | 40 | 61 |
| Security & context learning | 51 | 61 |
Shared benchmarks
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| APEX-Agentsindex | 54.5% | 75.5% |
| Vending-Bench 2index | $6,378 | $11,165 |
| CursorBenchindex | 34.1% | 55.5% |
| Chess Puzzles | 45.0% | 59.0% |
| CritPt | 16.9% | 31.4% |
| DTBench | 92.5% | 97.3% |
| FrontierCode | 42.7% | 52.1% |
| FrontierMath Tier 4 | 29.3% | 80.5% |
| FrontierMath Tiers 1-3 | 65.6% | 88.8% |
| GPQA Diamond | 90.5% | 95.6% |
| LMCA | 50.0% | 68.3% |
| MirrorCode | 63.3% | 97.8% |
| OTIS Mock AIME | 94.7% | 100.0% |
| ProofBench | 77.0% | 100.0% |
| SciCode | 54.3% | 61.0% |
| SimpleBench | 60.6% | 75.9% |
| SimpleQA Verified | 33.7% | 46.5% |
| WebDev Arena | 1537 | 1786 |
Specs and price
| Claude Sonnet 5 | Claude Sonnet 5.5 | |
|---|---|---|
| Agent Index | 52.4 (#32) | 69 (#9) |
| Agent $/M | $0.92 | $0.84 |
| Input / output $/M | $2.00 / $10.00 | $2.00 / $10.00 |
| Context | 1M | 1M |
| Released | Jun 30, 2026 | Sep 28, 2026 |
| Weights | Closed | Closed |
| API hosts | 5 | 5 |
Don’t pick one. Route.
Shogo can run Claude Sonnet 5 and Claude Sonnet 5.5 side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo