Claude Sonnet 5.5
Fast Claude model for everyday coding, agents, and knowledge work
Shogo Agent Index
Estimated#9 of 9269.0range 61.3–76.7 · 23% of weight measured
Agentic coding
79
26% measured
Long-horizon autonomy
75
30% measured
Knowledge-work agents
57
32% measured
Computer use
61
estimated
Security & context learning
61
estimated
Price
- Input
- $2.00/M
- Output
- $10.00/M
- Cache read
- $0.10/M
- 3:1 blend
- $4.00/M
- Agent-effective
- $0.84/M
Cheapest host for agents: Amazon Bedrock at $0.84/M.
Agent-effective = 20 input tokens per output token, 85% cache hits. Why.
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 88 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 95 | |
| DeepSWE | est. | 6% | predicted 78 | |
| FrontierSWE | 61.9% | 5% | proximus · $110.45/task | |
| CursorBench | 55.5% | 4% | source · $7.05/task | |
| GSO-Bench | est. | 4% | predicted 71 | |
| METR Time Horizons | est. | 10% | predicted 85 | |
| Vending-Bench 2 | $11,165 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 37 | |
| APEX-Agents | 75.5% | 8% | source | |
| GDPval | est. | 7% | predicted 68 | |
| Remote Labor Index | est. | 5% | predicted 17 | |
| DeepResearch Bench | est. | 5% | predicted 52 | |
| OSWorld 2.0 | est. | 6% | predicted 38 | |
| OSWorld | est. | 4% | predicted 94 | |
| Cybench | est. | 5% | predicted 93 | |
| CL-bench | est. | 5% | predicted 29 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 96.5% | source |
| ARC-AGI-2 | Reasoning | 83.9% | source |
| Chess Puzzles | Reasoning | 59.0% | source |
| CritPt | Reasoning | 31.4% | source |
| DTBench | Knowledge | 97.3% | source |
| FrontierCode | Coding | 52.1% | claude-code |
| FrontierMath Tiers 1-3 | Math | 88.8% | source |
| FrontierMath Tier 4 | Math | 80.5% | source |
| GPQA Diamond | Reasoning | 95.6% | source |
| Humanity's Last Exam | Reasoning | 46.1% | source |
| LMCA | Knowledge | 68.3% | source |
| MirrorCode | Coding | 97.8% | source |
| OTIS Mock AIME | Math | 100.0% | source |
| ProofBench | Math | 100.0% | source |
| SciCode | Coding | 61.0% | source |
| SimpleBench | Reasoning | 75.9% | source |
| SimpleQA Verified | Knowledge | 46.5% | source |
| WebDev Arena | Coding | 1786 | source |
| WeirdML v3 | Coding | 19.9% | claude_code |
API hosts
Live prices and uptime for every host serving Claude Sonnet 5.5 via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Amazon Bedrock | $2.00 | $10.00 | $0.10 | $0.84 | 100.0% | — |
| Anthropic | $2.00 | $10.00 | $0.10 | $0.84 | 100.0% | — |
| Azure | $2.00 | $10.00 | $0.10 | $0.84 | 100.0% | — |
| Claude Platform on AWS | $2.00 | $10.00 | $0.10 | $0.84 | 100.0% | — |
| $2.00 | $10.00 | $0.10 | $0.84 | 100.0% | — |