AN
Compare- Context window
- 1M
- Input
- Image · Text
- Output
- Text
- Released
- 2026-10-07
- Max output
- 128K
- Weights
- Closed
- Capabilities
- Reasoning, Temperature, Tool call
IN
$0.10
USD / 1,000,000 token
prompt: <=100000 input tokens
Cache write
$0.125 – $0.20
USD / 1,000,000 token
$0.125 · prompt: <=100000 input tokens; cache TTL: 5m
$0.20 · prompt: <=100000 input tokens; cache TTL: 1h
Cache read
$0.01
USD / 1,000,000 token
prompt: <=100000 input tokens
OUT
$0.50
USD / 1,000,000 token
prompt: <=100000 input tokens
Performance
Overall capability
60.5/100
- Coding
- 59.4
- Reasoning
- 58.8
- Professional work
- 56.9
- Knowledge & language
- 57.8
| AA-Analyst AgentClaude Haiku 5.5 (Max) | Professional work | Artificial Analysis | 2026-11-05 | |
| BullshitBench v2 | Knowledge & language | BullshitBench | 2026-11-05 | |
| Chess Puzzles | Reasoning | Epoch AI | 2026-11-05 | |
| Harvey Legal Agent Benchmark | Professional work | Vals AI / Harvey | 2026-11-05 | |
| SciCodeClaude Haiku 5.5 (Max) | Coding | Artificial Analysis | 2026-11-05 | |
| SimpleQA Verified | Knowledge & language | Epoch AI | 2026-11-05 | |
| AA-OmniscienceClaude Haiku 5.5 (Max) | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| Terminal-Bench Science（Vals 复跑） | Reasoning | Vals AI | 2026-11-05 |
Providers
| Input | Output | Cache read | Cache write | ||||
|---|---|---|---|---|---|---|---|
| Anthropic | claude-haiku-5-5 | Anthropic messages | - | - | - | - | - |
ModelRegistry · Catalog updated 2026-11-05