Claude Sonnet 5.5
Anthropic
87.5#6 of 427 overall
- Input / output
- US$ 2,00 / US$ 10,00 US$ per 1M tokens
- Context
- 1M tokens
- Release
- 09/28/2026 release date
- Weights
- Closed
- Speed
- 134 tok/s first token in 272.47 s
Family history
The 8 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | AA Intel. | Elo Arena |
|---|---|---|---|---|---|
| Claude 3 Sonnet | 03/04/2024 | 14.4 | #425 | — | 1218 |
| Claude 3.5 Sonnet | 10/22/2024 | 19.9 | #403 | — | 1298 |
| Claude 3.7 Sonnet | 02/24/2025 | 32.3 | #334 | — | 1314 |
| Claude 4 Sonnet | 05/22/2025 | 37.9 | #281 | — | 1351 |
| Claude Sonnet 4.5 | 09/29/2025 | 51.1 | #139 | — | 1439 |
| Claude Sonnet 4.6 | 02/17/2026 | 70.6 | #38 | — | 1458 |
| Claude Sonnet 5 | 06/30/2026 | 70.8 | #37 | — | 1443 |
| Claude Sonnet 5.5 | 09/28/2026 | 87.5 | #6 | 54.2 | 1473 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| LiveBench weight 3 | 80.0 | 87% | LiveBench |
| AA Intelligence Index weight 3 | 54.2 | 91% | Artificial Analysis |
| Arena text (Elo) weight 2 | 1473 | 87% | LMArena |
| Arena WebDev (Elo) weight 1 | 1770 | 98% | LMArena |
| Arena vision (Elo) weight 0.5 | 1287 | 79% | LMArena |
| Humanity's Last Exam weight 1 | 55.0 | 99% | Artificial Analysis |
| Terminal-Bench weight 1 | 63.6 | 99% | Artificial Analysis |
| Long-context reasoning | 82.7 | 94% | Artificial Analysis |
| LiveBench long agentic | 63.4 | 87% | LiveBench |
| LiveBench reasoning | 91.6 | 84% | LiveBench |
| LiveBench coding | 94.7 | 84% | LiveBench |
| LiveBench browser | 89.3 | 87% | LiveBench |
| LiveBench data analysis | 59.5 | 10% | LiveBench |
| LiveBench research | 83.6 | 84% | LiveBench |
| LiveBench design | 85.0 | 97% | LiveBench |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 78.6 | #4 | LiveBench long agentic, Terminal-Bench |
| Coding | 77.4 | #4 | LiveBench coding, Arena WebDev (Elo) |
| Reasoning | 77.6 | #27 | LiveBench reasoning, Humanity's Last Exam |
| Data analysis | 29.9 | #29 | LiveBench data analysis |
| Research | 76.0 | #4 | LiveBench research, Long-context reasoning |
| Design | 81.7 | #2 | LiveBench design, Arena WebDev (Elo) |
| Browser use | 68.5 | #5 | LiveBench browser |
| Chat | 68.7 | #25 | Arena text (Elo) |
| Vision | 64.3 | #23 | Arena vision (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.