#39 Claude Sonnet 5.5
max
OpenRouter returned no showcase content (finish_reason: length).
- Cost
- $0.000
- Time
- 571.7s
- Tokens
- 0 tok
Anthropic
Release: 2026-09-29
Tested on: 2026-09-29 21:38
anthropic/claude-sonnet-5.5::max
~1T total (~100B active)MoEClosedEstimated
Summary
Claude Sonnet 5.5 scores 9.0 on AI BENCHY and ranks #39. It has 10.0 reliability, a 81.8% pass rate, $7.545 total cost, and 83.04s average response time.
What makes Claude Sonnet 5.5 unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Model facts
Researched on 2026-09-29
- Parameters
- ~1T total (~100B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose parameter counts or architecture. Low-confidence catalog estimates carry forward the prior Claude Sonnet 5 family estimates; the announcement establishes identity and API availability, not these counts. Thinking is always on; OpenRouter lists low, medium, high, xhigh, and max efforts.
9.0
Consistency
9.4
10.0
$7.545
Total Output Tokens
727,349
Total Input Tokens
135,496
Input Price
$2.000 / 1M
Output Price
$10.000 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Claude Sonnet 5.5maxvsGPT-5.5mediumClaude Sonnet 5.5maxvsQwen3.8 MaxmediumClaude Sonnet 5.5maxvsGemini 3.5 FlashmediumClaude Sonnet 5.5maxvsGrok 4.5highClaude Sonnet 5.5maxvsClaude Fable 5.1highClaude Sonnet 5.5maxvsQwen3.8 Max (0902)highClaude Sonnet 5.5maxvsClaude Opus 5.5mediumClaude Sonnet 5.5maxvsGPT-5.3-CodexmediumClaude Sonnet 5.5maxvsQwen3.7 MaxmediumClaude Sonnet 5.5maxvsMuse Spark 1.3high
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 5.1 | 3.4 | |
| Instructions following | 8.5 | 6.8 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |