AnthropicClaude Sonnet 5.5
Claude Sonnet 5.5 is an Anthropic proprietary reasoning model, released 28 Sept 2026. Its best configuration (max reasoning effort) ranks #9 of 775 on the BenchLeader Index at 69.5 ±5.2, in the top ten. The ± is the point: 59 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (92) and lowest in knowledge (65). At $4.00 per million tokens blended it is among the most expensive ranked models. Output speed of 137 tokens per second puts it faster than most, with a first answer in 428.3 s. It has been measured at 6 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 19 Oct 2026.
- Blended price
- $4.00/M
- $2.00 in · $10.00 out
- Output speed
- 137 tok/s
- measured by Artificial Analysis
- First answer
- 428 s
- first token 1.88 s
- Context
- 1M
- Full answer
- 432 s
- median, reasoning included
- Cost per run
- $5.46
- one full Intelligence Index run
- Released
- 28 Sept 2026
- Overall index70
- Reasoning81
- Coding69
- Agents & tools70
- Maths72
- Knowledge65
- Long context67
- Composite92
Versions
Anthropic has shipped 10 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Claude Sonnet 5.5maxthis page | 28 Sept 2026 | 69.5 | #9 |
| Claude Sonnet 5high | 30 Jun 2026 | 60.3 | #114 |
| Claude Sonnet 4.6 | 17 Feb 2026 | 57.1 | #183 |
| Claude Sonnet 4.5high | 29 Sept 2025 | 58.3 | #156 |
| Claude Sonnet 4thinking | 22 May 2025 | 53.3 | #286 |
| Claude 3.7 Sonnetthinking | 24 Feb 2025 | 51.1 | #347 |
| Claude 3.5 Sonnet | 22 Oct 2024 | 46.3 | #482 |
| Claude 3 Sonnet | 29 Feb 2024 | 38.1 | #707 |
| Claude 37 Sonnetthinking | – | – | – |
| Claude Sonnet 5.0max | – | – | – |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| low | 58.2 | #160 | 106 tok/s | 1.11 s | $0.0038 | Coding 53 · Composite 70 · Knowledge 70 · Long context 63 · Reasoning 60 |
| medium | 58.9 | #142 | 107 tok/s | 1.37 s | $0.0038 | Agents & tools 44 · Coding 58 · Composite 75 · Knowledge 71 · Long context 63 · Reasoning 69 |
| high | 65.7 | #36 | 105 tok/s | 12 s | $0.0038 | Coding 70 · Composite 82 · Knowledge 71 · Long context 64 · Reasoning 81 |
| xhigh | 67.9 | #18 | 110 tok/s | 33 s | $0.0038 | Coding 72 · Composite 88 · Human preference 67 · Knowledge 72 · Long context 65 · Maths 69 · Multimodal 63 · Reasoning 81 |
| maxbest | 69.5 | #9 | 137 tok/s | 428 s | $0.0038 | Agents & tools 70 · Coding 69 · Composite 92 · Knowledge 65 · Long context 67 · Maths 72 · Reasoning 81 |
| not stated | – | – | 103 tok/s | 1.88 s | $0.0038 | Agents & tools 69 · Coding 66 · Composite 66 |
What more thinking costs
Turning the effort up buys index points and multiplies the bill. Here max costs 16× low for +11.3 on the index — 2.8 points per doubling of spend. Compare that with other models.
How its index has moved
29 Sept 2026 to 20 Oct 2026- max
- xhigh
- high
- medium
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | – | – | 95.6%#3 | – | Epoch AI Benchmarking Hub | |
| Humanity's Last Exam | – | – | – | 46.1%#4 | – | – | Scale AI / CAIS | |
| Arena Hard Prompts | – | – | – | 1504#24 | – | – | Arena (LMArena) | |
| LiveBench 2.0 Reasoningnot in indexeffort not stated | – | – | – | – | – | 91.6%#7 | LiveBench | |
| LiveBench 1.0 Reasoningnot in index | – | – | – | 86.8%#30 | 91.6%#6 | – | LiveBench | |
| Humanity's Last Exam (AA)not in index | 36.2%#111 | 39.8%#86 | 45.8%#47 | 50.0%#25 | 55.0%#9 | – | Artificial Analysis | |
| CritPt | 11.4%#110 | 16.9%#81 | 24.6%#46 | 31.1%#10 | 31.4%#8 | – | Artificial Analysis | |
| MysteryMechanismnot in indexeffort not stated | – | – | – | – | – | 49.1%#3 | Vals AI | |
| Chess Puzzlesnot in index | – | – | – | – | 59.0%#10 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | 65.0%#4 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | 64.5%#14 | 65.5%#9 | 65.9%#5 | 66.3%#3 | 68.3%#1 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 93.3%#64 | 93.9%#60 | 94.1%#58 | 96.0%#30 | 97.3%#9 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SciCode | 49.1%#117 | 52.9%#83 | 53.7%#71 | 57.3%#31 | 61.0%#5 | – | SciCode | |
| FrontierCode | – | – | – | 52.1%#5 | – | – | Cognition | |
| Arena Coding | – | – | – | 1530#21 | – | – | Arena (LMArena) | |
| Arena WebDev | – | – | 1710#7 | 1768#3 | – | – | Arena (LMArena) | |
| LiveBench 2.0 Codingnot in indexeffort not stated | – | – | – | – | – | 94.7%#6 | LiveBench | |
| LiveBench 1.0 Codingnot in index | – | – | – | 88.9%#4 | 91.4%#1 | – | LiveBench | |
| SciCode (AA)not in index | 49.1%#118 | 52.9%#82 | 53.7%#74 | 57.3%#30 | 61.0%#6 | – | Artificial Analysis | |
| IOIeffort not stated | – | – | – | – | – | 83.1%#9 | Vals AI | |
| Code Migrationnot in indexeffort not stated | – | – | – | – | – | 69.8%#1 | Vals AI | |
| ProgramBenchnot in indexeffort not stated | – | – | – | – | – | 6.5%#3 | Vals AI | |
| Vibe Code Bench v1.1not in indexeffort not stated | – | – | – | – | – | 92.4%#1 | Vals AI | |
| CursorBenchnot in index | 35.8%#50 | 39.2%#41 | 47.8%#17 | 53.1%#5 | 55.5%#4 | – | Cursor | |
| ALE-Benchnot in index | – | – | 1819.1#12 | – | – | – | Epoch AI Benchmarking Hub | |
| FrontierSWEnot in index | – | – | – | – | 61.9%#3 | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 20.7%#61 | 29.8%#46 | 43.9%#25 | 57.1%#6 | 63.6%#1 | – | Artificial Analysis | |
| Startrise Frontendnot in index | – | – | 72.8%#13 | – | – | 75.9%#7 | Startrise | |
| FrontierCode 1.1 (AA)not in index | 26.4%#40 | 29.3%#38 | 44.3%#12 | 46.1%#8 | 45.8%#9 | – | Artificial Analysis |
Agents & tools
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | – | 61.8%#14 | – | Terminal-Bench | |
| APEX-Agents | – | 44.6%#38 | – | – | 75.5%#2 | – | Mercor | |
| Arena Agent | – | – | – | – | 12.8#5 | – | Arena (LMArena) | |
| LiveBench Long Agenticnot in indexeffort not stated | – | – | – | – | – | 78.8%#4 | LiveBench | |
| LiveBench Browsernot in indexeffort not stated | – | – | – | – | – | 84.0%#10 | LiveBench | |
| LiveBench Agentic Codingnot in index | – | – | – | 39.3%#63 | 56.3%#28 | – | LiveBench | |
| Terminal-Bench 2.1 (Vals)effort not stated | – | – | – | – | – | 83.2%#6 | Vals AI | |
| GDPval-AA v2.1not in index | 33.8%#125 | 41.2%#98 | 52.5%#42 | 61.4%#9 | 66.9%#3 | – | Artificial Analysis | |
| Analyst Agent (AA)not in index | – | – | – | – | 57.5%#2 | – | Artificial Analysis | |
| CyberBenchnot in indexeffort not stated | – | – | – | – | – | 59.6%#34 | Vals AI | |
| Finance Agent v2not in indexeffort not stated | – | – | – | – | – | 58.1%#12 | Vals AI | |
| Harvey's Legal Agent Benchmarknot in indexeffort not stated | – | – | – | – | – | 10.4%#13 | Vals AI | |
| Legal Research Benchnot in indexeffort not stated | – | – | – | – | – | 48.1%#10 | Vals AI | |
| SREBenchnot in indexeffort not stated | – | – | – | – | – | 30.1%#8 | Vals AI | |
| Tax Agent Benchnot in indexeffort not stated | – | – | – | – | – | 42.0%#8 | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in indexeffort not stated | – | – | – | – | – | 64.1%#2 | Vals AI | |
| Terminal-Bench Sciencenot in indexeffort not stated | – | – | – | – | – | 47.1%#3 | Vals AI | |
| Vending-Bench 2not in indexeffort not stated | – | – | – | – | – | 11165.3#5 | Andon Labs | |
| AutomationBenchnot in index | 49.4%#78 | 54.9%#58 | 59.4%#39 | 65.5%#16 | 71.8%#3 | – | Artificial Analysis | |
| GDP.pdf (AA)not in index | 16.0%#90 | 20.2%#62 | 25.2%#29 | 24.6%#31 | 25.8%#26 | – | Artificial Analysis | |
| Harvey LAB-AA v1.1not in index | – | – | – | – | 2.8%#14 | – | Harvey | |
| AA-Briefcase v1.1not in index | – | – | 1636#12 | 1751#4 | 1817#1 | – | Artificial Analysis | |
| Terminal-Bench-Science 0.1 (AA)not in index | 10.5%#25 | 16.2%#20 | 34.3%#11 | 52.4%#7 | 53.3%#5 | – | Artificial Analysis |
Maths
| Benchmark | xhigh | max | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | 88.8%#7 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | 80.5%#13 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | 100.0%#1 | Epoch AI Benchmarking Hub | |
| ProofBench | – | 100.0%#1 | Vals AI | |
| LiveBench Mathematicsnot in index | 96.7%#6 | 96.1%#11 | LiveBench | |
| Arena Maths | 1502#15 | – | Arena (LMArena) |
Knowledge
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | – | – | 46.5%#36 | – | Epoch AI Benchmarking Hub | |
| LiveBench 2.0 Data Analysisnot in indexeffort not stated | – | – | – | – | – | 59.5%#42 | LiveBench | |
| LiveBench Researchnot in indexeffort not stated | – | – | – | – | – | 83.6%#10 | LiveBench | |
| LiveBench 1.0 Data Analysisnot in index | – | – | – | 78.6%#22 | 59.5%#61 | – | LiveBench | |
| AA-Omniscience | 19.4#71 | 20.1#68 | 20.9#63 | 23.5#55 | 32.3#26 | – | Artificial Analysis | |
| BioMysteryBenchnot in indexeffort not stated | – | – | – | – | – | 81.1%#1 | Vals AI | |
| Excel Modeling Benchmarknot in indexeffort not stated | – | – | – | – | – | 75.7%#3 | Vals AI | |
| MedCodenot in indexeffort not stated | – | – | – | – | – | 52.9%#12 | Vals AI | |
| MedScribenot in indexeffort not stated | – | – | – | – | – | 91.1%#3 | Vals AI | |
| Public Benefits Benchnot in indexeffort not stated | – | – | – | – | – | 67.2%#14 | Vals AI | |
| GDP.pdfnot in index | – | – | – | – | 31.4%#3 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 46.3%#81 | 47.2%#76 | 52.0%#54 | 53.0%#49 | 54.0%#43 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 49.8%#116 | 48.8%#122 | 35.4%#187 | 37.1%#177 | 53.0%#106 | – | Artificial Analysis |
Instruction following
| Benchmark | xhigh | max | Source | Trend |
|---|---|---|---|---|
| LiveBench Languagenot in index | 83.4%#19 | 78.0%#39 | LiveBench | |
| LiveBench Instruction Followingnot in index | 70.5%#28 | 56.8%#61 | LiveBench | |
| Arena Instruction Followingnot in index | 1483#19 | – | Arena (LMArena) |
Human preference
| Benchmark | xhigh | Source | Trend |
|---|---|---|---|
| Arena Text | 1475#36 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1465#22 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1472#56 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1499#18 | Arena (LMArena) |
Multimodal
| Benchmark | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|
| Arena Vision | 1287#30 | – | – | Arena (LMArena) | |
| LiveBench Designnot in indexeffort not stated | – | – | 85.0%#2 | LiveBench | |
| SAGEnot in indexeffort not stated | – | – | 51.8%#11 | Vals AI | |
| Blueprint-Bench 2not in indexeffort not stated | – | – | 39.3%#5 | Epoch AI Benchmarking Hub | |
| AA-3Dnot in index | – | 1197#1 | – | Artificial Analysis |
Long context
| Benchmark | low | medium | high | xhigh | max | Source | Trend |
|---|---|---|---|---|---|---|---|
| AA-LCR | 76.0%#147 | 76.3%#144 | 78.0%#120 | 79.7%#87 | 82.7%#35 | Artificial Analysis | |
| MLCRnot in index | – | – | – | – | 75.0%#1 | Artificial Analysis |
Composite
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | – | – | 166.2#6 | Epoch AI Benchmarking Hub | |
| LiveBench 2.0effort not stated | – | – | – | – | – | 82.5%#7 | LiveBench | |
| LiveBench 1.0not in index | – | – | – | 77.8%#22 | 75.7%#36 | – | LiveBench | |
| AA Intelligence Index v4.3.2 | 35.9#86 | 40.8#60 | 46.8#30 | 51.9#12 | 56#2 | – | Artificial Analysis | |
| Vals Indexnot in indexeffort not stated | – | – | – | – | – | 70.8#1 | Vals AI |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Google Vertex | 109 tok/s | 2.46 s | $2.00 | $10.00 | 1M | – |
| Google Vertex | 109 tok/s | 1.01 s | $2.20 | $11.00 | 1M | – |
| Anthropic | 105 tok/s | 1.58 s | $2.00 | $10.00 | 1M | – |
| Google Vertex | 89 tok/s | 1.01 s | $2.20 | $11.00 | 1M | – |
| Claude Platform on AWS | 84 tok/s | 0.99 s | $2.00 | $10.00 | 1M | – |
| Amazon Bedrock | 73 tok/s | 2.48 s | $2.00 | $10.00 | 1M | – |
| Azure | 62 tok/s | 0.97 s | $2.00 | $10.00 | 1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.100 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0038 | $0.0032 | 7.2 min |
| Summarize a 30-page report | 12,000 / 600 | $0.030 | $0.013 | 7.2 min |
| Code edit | 6,000 / 1,500 | $0.027 | $0.018 | 7.3 min |
| Agentic coding session | 60,000 / 4,000 | $0.160 | $0.074 | 7.6 min |
| Structured extraction | 2,000 / 200 | $0.0060 | $0.0032 | 7.2 min |
More from Anthropic
Compare Claude Sonnet 5.5 with…
- Claude Sonnet 5.5 vs Claude Opus 5.5
- Claude Sonnet 5.5 vs Gemini 4 Argon
- Claude Sonnet 5.5 vs Muse Wonder Full
- Claude Sonnet 5.5 vs GPT-6 Astra
- Claude Sonnet 5.5 vs Claude Fable 5.1
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Claude Sonnet 5.5 vs Claude Fable 5
- Claude Sonnet 5.5 vs Claude Opus 5
- Claude Sonnet 5.5 vs GPT-5.6 Sol
- Claude Sonnet 5.5 vs Muse Wonder
- Claude Sonnet 5.5 vs Muse Spark 1.3
- Claude Sonnet 5.5 vs GPT-6 Sol
- Claude Sonnet 5.5 vs GPT-5.5
- Claude Sonnet 5.5 vs GPT-5.5 Pro
- Claude Sonnet 5.5 vs Kimi K3
- Claude Sonnet 5.5 vs GPT-5.4
- Claude Sonnet 5.5 vs Gemini 3.8 Flash
- Claude Sonnet 5.5 vs Muse Spark
- Claude Sonnet 5.5 vs GPT-5.6 Terra
- Claude Sonnet 5.5 vs MiMo-V2.6-Pro
- Claude Sonnet 5.5 vs Grok 4.6
- Claude Sonnet 5.5 vs Grok 4.7
- Claude Sonnet 5.5 vs GPT-5.3-Codex
- Claude Sonnet 5.5 vs GLM 5.3
- Claude Sonnet 5.5 vs Gemini 3.7 Flash
- Claude Sonnet 5.5 vs GPT-5.4 Pro
- Claude Sonnet 5.5 vs Claude Opus 4.7
- Claude Sonnet 5.5 vs Claude Opus 4.8
- Claude Sonnet 5.5 vs Qwen3.8 Max
- Claude Sonnet 5.5 vs Gemini 3.5 Flash
- Claude Sonnet 5.5 vs Muse Spark 1.2
- Claude Sonnet 5.5 vs Qwen3.8 2.4T A95B
- Claude Sonnet 5.5 vs DeepSeek V4.1 Flash 1017
- Claude Sonnet 5.5 vs Muse Spark 1.1
- Claude Sonnet 5.5 vs Claude Opus 4.6
- Claude Sonnet 5.5 vs GLM 5.3 Flash
- Claude Sonnet 5.5 vs DeepSeek V4 Pro
- Claude Sonnet 5.5 vs GLM 5.2
- Claude Sonnet 5.5 vs Qwen3.6 Max
- Claude Sonnet 5.5 vs Gemini 3.6 Flash
- Claude Sonnet 5.5 vs MiniMax-M3.1-Flash
- Claude Sonnet 5.5 vs Claude Haiku 5.5
- Claude Sonnet 5.5 vs Muse Spark Open
- Claude Sonnet 5.5 vs DeepSeek V4 Flash
- Claude Sonnet 5.5 vs Gemini 3.1 Pro
- Claude Sonnet 5.5 vs Qwen3 7
- Claude Sonnet 5.5 vs GPT-5.2
- Claude Sonnet 5.5 vs Step 5 Preview
- Claude Sonnet 5.5 vs Gemini 3 Pro
- Claude Sonnet 5.5 vs Claude Sonnet 5
- Claude Sonnet 5.5 vs Qwen3.8-Flash-Next
- Claude Sonnet 5.5 vs GPT-6 Luna
- Claude Sonnet 5.5 vs Claude Opus 4.5
- Claude Sonnet 5.5 vs GPT-5.6 Luna
- Claude Sonnet 5.5 vs MiMo-V2.6-Flash
- Claude Sonnet 5.5 vs GPT-5 Pro
- Claude Sonnet 5.5 vs o3
- Claude Sonnet 5.5 vs Kimi K2.6
- Claude Sonnet 5.5 vs GPT-5.2-Codex
See also
Data as of 21 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Claude Sonnet 5.5: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/claude-sonnet-5-5, data as of 21 Oct 2026.