AnthropicClaude Opus 5.5
No cheaper ranked model scores higher: it is on the price frontier.
As of 9 Nov 2026, Claude Opus 5.5 by Anthropic scores 68.9 on the BenchLeader Index (top 10 of 599 ranked configurations), with its best results in coding (80) and weakest in agents & tools (63). API pricing: $4.00 per 1M input tokens and $20.00 per 1M output tokens ($8.00 blended at 3:1), list price on 9 Nov 2026. It streams about 110 tokens/s (Artificial Analysis). Released 22 Sep 2026.
Key facts (as of 9 Nov 2026)
- Claude Opus 5.5 API pricing: $4.00 per 1M input tokens and $20.00 per 1M output tokens ($8.00 blended at 3:1) (list price, 9 Nov 2026).
- Claude Opus 5.5 streams about 110 tokens/s (Artificial Analysis, 9 Nov 2026).
- Claude Opus 5.5 was released on 22 Sep 2026 (Anthropic).
In detail. Claude Opus 5.5 is an Anthropic proprietary reasoning model, released 22 Sep 2026. Its best configuration (max reasoning effort) ranks #2 of 599 on the BenchLeader Index at 68.9 ±4.6, in the top ten. The ± is the point: 30 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 coding (80) and lowest in agents & tools (63). At $8.00 per million tokens blended it is among the most expensive ranked models. Output speed of 115 tokens per second puts it faster than most, with a first answer in 380.6 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 8 Nov 2026.
- Blended price
- $8.00/M
- $4.00 in · $20.00 out
- via Artificial Analysis
- Output speed
- 115 tok/s
- measured by Artificial Analysis
- First answer
- 381 s
- first token 3.12 s
- Context
- 1M
- via models.dev
- Full answer
- 771 s
- median, reasoning included
- Cost per task
- $10.04
- 25 min a task, AA Index
- Tokens per task
- 173k
- 70% of it reasoning
- Released
- 22 Sep 2026
- Overall index69
- Reasoning72
- Coding80
- Agents & tools63
- Maths74
- Knowledge74
- Multimodal70
- Long context67
Versions
Anthropic has shipped 9 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 Opus 5.5maxthis page | 22 Sep 2026 | 68.9 | #2 |
| Claude Opus 5 | 24 Jul 2026 | 65.2 | #21 |
| Claude Opus 4.8high | 28 May 2026 | 60.5 | #76 |
| Claude Opus 4.7 | 16 Apr 2026 | 63.2 | #42 |
| Claude Opus 4.6high | 5 Feb 2026 | 62.7 | #48 |
| Claude Opus 4.5thinking | 24 Nov 2025 | 59.7 | #97 |
| Claude Opus 4.1thinking | 5 Aug 2025 | 57.9 | #146 |
| Claude Opus 4thinking | 22 May 2025 | 55.2 | #211 |
| Claude 3 Opus | 4 Mar 2024 | 38.9 | #544 |
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 | 59.0 | #109 | 105 tok/s | 5.78 s | $0.0076 | Coding 52 · Knowledge 66 · Long context 65 · Multimodal 67 · Reasoning 60 |
| medium | 61.5 | #66 | 103 tok/s | 14 s | $0.0076 | Agents & tools 52 · Coding 66 · Knowledge 67 · Long context 67 · Multimodal 68 · Reasoning 68 |
| high | 65.4 | #18 | 105 tok/s | 28 s | $0.0076 | Coding 67 · Human preference 70 · Knowledge 68 · Long context 66 · Maths 70 · Multimodal 68 · Reasoning 70 |
| xhigh | 65.5 | #16 | 106 tok/s | 84 s | $0.0076 | Coding 75 · Knowledge 69 · Long context 67 · Multimodal 69 · Reasoning 74 |
| maxbest | 68.9 | #2 | 115 tok/s | 381 s | $0.0076 | Agents & tools 63 · Coding 80 · Knowledge 74 · Long context 67 · Maths 74 · Multimodal 70 · Reasoning 72 |
| not stated | 63.2 | #43 | 78 tok/s | 3.12 s | $0.0076 | Agents & tools 68 · Coding 74 · Composite 72 · Human preference 72 · Knowledge 55 |
What more thinking costs
Turning the effort up buys index points and multiplies the bill. Here max costs 10× low for +9.9 on the index — 2.9 points per doubling of spend. Compare that with other models.
Each point is one reasoning setting: its cost per Artificial Analysis index task (log scale) and its BenchLeader Index.
How its index has moved
23 Sep 2026 to 9 Nov 2026- max
- xhigh
- high
- not stated
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 | – | – | – | – | 90.6%#44 | – | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | – | – | 1530#5 | – | – | – | Arena (LMArena) | |
| LiveBench 2.0 Reasoningnot in indexeffort not stated | – | – | – | – | – | 92.2%#4 | LiveBench | |
| LiveBench 1.0 Reasoningnot in index | – | – | – | 90.7%#10 | 92.2%#3 | – | LiveBench | |
| Humanity's Last Exam (AA)not in index | 48.3%#39 | 54.7%#16 | 55.6%#12 | 57.5%#9 | 61.4%#5 | – | Artificial Analysis | |
| HLE-Diamond (AA) | 41.7%#34 | 51.4%#23 | 55.6%#19 | 64.0%#8 | 67.9%#5 | – | Artificial Analysis | |
| ARC-AGI-1 | 88.5%#94 | 97.5%#13 | 98.5%#1 | 97.5%#13 | 97.5%#13 | – | ARC Prize | |
| ARC-AGI-2 | 70.1%#65 | 87.5%#27 | 93.3%#4 | 92.5%#6 | 91.7%#11 | – | ARC Prize | |
| CritPtnot in index | 17.7%#83 | 27.7%#35 | 30.9%#15 | 31.7%#6 | 31.7%#6 | – | Artificial Analysis | |
| CritPt v2 hard subset (AA) | 36.0%#61 | 54.0%#34 | 59.5%#28 | 67.5%#15 | 68.0%#13 | – | Artificial Analysis | |
| MysteryMechanismnot in indexeffort not stated | – | – | – | – | – | 49.5%#3 | Vals AI | |
| Chess Puzzlesnot in index | – | – | – | – | 67.0%#5 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | 71.0%#4 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | 64.9%#13 | 65.7%#7 | 65.9%#6 | 66.2%#4 | 68.2%#2 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 95.5%#38 | 96.5%#22 | 96.5%#22 | 97.3%#9 | 98.9%#1 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SciCode | 58.6%#25 | 59.3%#16 | 60.4%#11 | 65.0%#2 | 66.9%#1 | – | SciCode | |
| FrontierCode | – | 54.6%#1 | – | – | – | – | Cognition | |
| Arena Coding | – | – | 1546#10 | – | – | – | Arena (LMArena) | |
| Arena WebDev | – | – | – | – | 1818#1 | – | Arena (LMArena) | |
| LiveBench 2.0 Codingnot in indexeffort not stated | – | – | – | – | – | 87.1%#4 | LiveBench | |
| LiveBench 1.0 Codingnot in index | – | – | – | 89.3%#2 | 89.3%#2 | – | LiveBench | |
| SciCode (AA)not in index | 58.6%#27 | 59.3%#20 | 60.4%#13 | 65.0%#4 | 66.9%#2 | – | Artificial Analysis | |
| IOIeffort not stated | – | – | – | – | – | 95.1%#4 | Vals AI | |
| Code Migrationnot in indexeffort not stated | – | – | – | – | – | 66.7%#4 | Vals AI | |
| Code Migration v1.1not in indexeffort not stated | – | – | – | – | – | 81.0%#3 | Vals AI | |
| ProgramBenchnot in indexeffort not stated | – | – | – | – | – | 18.5%#2 | Vals AI | |
| SWE-bench Multimodalnot in indexeffort not stated | – | – | – | – | – | 70.2%#1 | Vals AI | |
| Vibe Code Bench 1-100not in indexeffort not stated | – | – | – | – | – | 30.4%#2 | Vals AI | |
| Vibe Code Bench v1.1not in indexeffort not stated | – | – | – | – | – | 90.3%#6 | Vals AI | |
| MirrorCodenot in index | – | – | 78.9%#1 | – | – | – | Epoch AI Benchmarking Hub | |
| CursorBenchnot in index | 43.7%#32 | 52.5%#8 | 56.0%#2 | 56.0%#2 | 57.8%#1 | – | Cursor | |
| ALE-Benchnot in index | – | – | 2147.4#7 | – | – | – | Epoch AI Benchmarking Hub | |
| FrontierSWEnot in index | – | – | – | – | 62.3%#2 | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 31.3%#60 | 52.5%#24 | 56.6%#16 | 59.6%#7 | 59.6%#7 | – | Artificial Analysis | |
| Startrise Frontendnot in index | – | – | 80.2%#5 | – | – | 71.1%#23 | Startrise | |
| GameBench 2 Overallnot in indexacross settings | – | – | – | – | – | 87.6#2 | DuelLab GameBench 2 | |
| GameBench 2 by reasoning settingnot in index | 76.3#21 | 91.5#5 | – | 94.8#1 | – | – | DuelLab GameBench 2 | |
| Design Arena Websitenot in indexeffort not stated | – | – | – | – | – | 1325#9 | Design Arena | |
| FrontierCode 1.1 (AA)not in index | 42.7%#31 | 57.0%#3 | 54.0%#7 | 53.5%#8 | 52.2%#9 | – | Artificial Analysis | |
| FrontierCode 2.0 (AA) | 15.8%#77 | 33.1%#30 | 35.9%#22 | 43.8%#5 | 46.4%#4 | – | Artificial Analysis |
Agents & tools
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | – | 65.8%#9 | – | Terminal-Bench | |
| Remote Labor Indexeffort not stated | – | – | – | – | – | 21.3%#1 | Scale AI / CAIS | |
| APEX-Agents | – | 52.5%#28 | – | – | 73.5%#3 | – | Mercor | |
| Arena Agent | – | – | – | – | 20#1 | – | Arena (LMArena) | |
| LiveBench Long Agenticnot in indexeffort not stated | – | – | – | – | – | 72.8%#4 | LiveBench | |
| LiveBench Browsernot in indexeffort not stated | – | – | – | – | – | 88.4%#6 | LiveBench | |
| LiveBench Agentic Codingnot in index | – | – | – | 65.3%#4 | 71.7%#2 | – | LiveBench | |
| Terminal-Bench 2.1 (Vals)effort not stated | – | – | – | – | – | 87.6%#1 | Vals AI | |
| MCP Atlaseffort not stated | – | – | – | – | – | 85.4%#5 | Scale AI SEAL | |
| HiL-Bencheffort not stated | – | – | – | – | – | 59.0%#11 | Scale AI SEAL | |
| GDPval-AA v2.1, normalised scorenot in index | 36.7%#69 | 54.3%#27 | 60.2%#13 | 66.5%#5 | 68.3%#1 | – | Artificial Analysis | |
| GDPval-AA v2.1not in index | 1240#72 | 1593#29 | 1714#15 | 1835#5 | 1866#1 | – | Artificial Analysis | |
| ITBench SRE (AA)not in index | – | – | – | – | 38.2%#23 | – | Artificial Analysis | |
| Analyst Agent (AA)not in index | – | – | – | – | 56.3%#4 | – | Artificial Analysis | |
| CUA-benchnot in index | – | – | – | – | 14.0%#2 | – | Vals AI | |
| CyberBenchnot in indexeffort not stated | – | – | – | – | – | 55.4%#40 | Vals AI | |
| Finance Agent v2not in indexeffort not stated | – | – | – | – | – | 58.6%#11 | Vals AI | |
| Finance Agent v2.1not in indexeffort not stated | – | – | – | – | – | 67.8%#2 | Vals AI | |
| Harvey's Legal Agent Benchmark v1.1not in indexeffort not stated | – | – | – | – | – | 9.2%#24 | Vals AI | |
| Harvey's Legal Agent Benchmark v1not in indexeffort not stated | – | – | – | – | – | 3.8%#41 | Vals AI | |
| Legal Research Benchnot in indexeffort not stated | – | – | – | – | – | 50.5%#7 | Vals AI | |
| Robo-benchnot in index | – | – | – | – | 14.6%#3 | – | Vals AI | |
| SREBenchnot in indexeffort not stated | – | – | – | – | – | 33.6%#4 | Vals AI | |
| Tax Agent Benchnot in indexeffort not stated | – | – | – | – | – | 44.5%#6 | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in indexeffort not stated | – | – | – | – | – | 65.2%#1 | Vals AI | |
| Terminal-Bench Sciencenot in indexeffort not stated | – | – | – | – | – | 47.1%#4 | Vals AI | |
| Time Horizon Index: KSPnot in indexeffort not stated | – | – | – | – | – | 91.3%#1 | Vals AI | |
| Arena Searchnot in index | – | 1214#10 | – | – | – | – | Arena (LMArena) | |
| Vending-Bench 2not in indexeffort not stated | – | – | – | – | – | 9235.3#11 | Andon Labs | |
| AutomationBenchnot in index | 52.9%#91 | 61.2%#45 | 63.2%#38 | 65.0%#31 | 69.5%#11 | – | Artificial Analysis | |
| GDP.pdf (AA)not in index | 25.6%#37 | 25.6%#37 | 28.8%#15 | 26.6%#29 | 26.2%#32 | – | Artificial Analysis | |
| Harvey LAB-AA v1.1not in index | – | – | – | – | 4.2%#12 | – | Harvey | |
| AA-Briefcase v1.1not in index | 1279#77 | 1620#18 | 1682#8 | 1760#4 | 1800#2 | – | Artificial Analysis | |
| GDPxnot in index | – | – | – | – | 12.0%#1 | – | GDPx by SemiAnalysis | |
| Design Arena Agenticnot in index | – | – | 1461#1 | – | – | 1334#4 | Design Arena | |
| Terminal-Bench-Science 0.1 (AA)not in index | 24.3%#39 | 43.3%#23 | 49.0%#21 | 61.9%#7 | 59.0%#11 | – | Artificial Analysis | |
| CWE-Bench (AA) | – | – | – | – | 58.3%#8 | – | Artificial Analysis | |
| DeepSec-Bench (AA) | – | – | – | – | 26.9%#6 | – | Artificial Analysis | |
| CyberGym end-to-end (AA) | – | – | – | – | 0.8%#17 | – | Artificial Analysis | |
| FACTS Searchnot in indexeffort not stated | – | – | – | – | – | 88.4%#7 |
Maths
| Benchmark | high | xhigh | max | Source | Trend |
|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | – | 91.2%#3 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | – | 95.0%#6 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | – | 100.0%#1 | Epoch AI Benchmarking Hub | |
| ProofBench | – | – | 100.0%#1 | Vals AI | |
| LiveBench Mathematicsnot in index | – | 96.8%#5 | 97.1%#1 | LiveBench | |
| Arena Maths | 1518#6 | – | – | Arena (LMArena) |
Knowledge
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | – | – | 72.2%#5 | – | Epoch AI Benchmarking Hub | |
| LiveBench 2.0 Data Analysisnot in indexeffort not stated | – | – | – | – | – | 80.3%#7 | LiveBench | |
| LiveBench Researchnot in indexeffort not stated | – | – | – | – | – | 88.9%#6 | LiveBench | |
| LiveBench 1.0 Data Analysisnot in index | – | – | – | 79.8%#11 | 80.3%#8 | – | LiveBench | |
| AA-Omniscience v1.1 | 39.0#26 | 39.8#24 | 42.4#16 | 43.1#14 | 48.1#7 | – | Artificial Analysis | |
| PRBench Legaleffort not stated | – | – | – | – | – | 47.6%#20 | Scale AI SEAL | |
| BioMysteryBenchnot in indexeffort not stated | – | – | – | – | – | 79.3%#4 | Vals AI | |
| ClaimBenchnot in indexeffort not stated | – | – | – | – | – | 100.0%#1 | Vals AI | |
| Excel Modeling Benchmarknot in indexeffort not stated | – | – | – | – | – | 75.9%#2 | Vals AI | |
| Excel Modeling Benchmark v1.1not in indexeffort not stated | – | – | – | – | – | 75.8%#5 | Vals AI | |
| MedCodenot in indexeffort not stated | – | – | – | – | – | 49.8%#19 | Vals AI | |
| MedScribenot in indexeffort not stated | – | – | – | – | – | 91.4%#1 | Vals AI | |
| Public Benefits Bench v1.1not in indexeffort not stated | – | – | – | – | – | 70.6%#4 | Vals AI | |
| EBR-benchnot in index | – | – | – | – | 71.4%#3 | – | Epoch AI Benchmarking Hub | |
| GDP.pdfnot in index | – | – | – | – | 30.6%#7 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience v1.1: accuracynot in index | 63.3%#13 | 63.9%#12 | 64.8%#10 | 65.5%#8 | 65.5%#9 | – | Artificial Analysis | |
| AA-Omniscience v1.1: non-hallucinationnot in index | 33.7%#95 | 33.1%#97 | 36.1%#91 | 35.0%#93 | 49.7%#72 | – | Artificial Analysis | |
| HealthBench Professional (AA)not in index | – | – | – | – | 59.9%#11 | – | OpenAI |
Instruction following
| Benchmark | high | xhigh | max | Source | Trend |
|---|---|---|---|---|---|
| LiveBench Languagenot in index | – | 85.5%#12 | 86.3%#10 | LiveBench | |
| LiveBench Instruction Followingnot in index | – | 67.0%#39 | 65.7%#43 | LiveBench | |
| Arena Instruction Followingnot in index | 1519#3 | – | – | Arena (LMArena) |
Human preference
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Text | 1506#4 | – | Arena (LMArena) | |
| EQ-Bench 4effort not stated | – | 1340#2 | EQ-Bench | |
| Arena Creative Writingnot in index | 1517#3 | – | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1500#12 | – | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1520#5 | – | Arena (LMArena) |
Multimodal
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Arena Vision | – | – | 1324#2 | – | – | – | Arena (LMArena) | |
| LiveBench Designnot in indexeffort not stated | – | – | – | – | – | 83.3%#2 | LiveBench | |
| MMMU-Pro | 84.7%#18 | 85.7%#9 | 85.8%#8 | 86.6%#4 | 87.7%#2 | – | Artificial Analysis | |
| SAGEnot in indexeffort not stated | – | – | – | – | – | 91.3%#1 | Vals AI | |
| Blueprint-Bench 2not in indexeffort not stated | – | – | – | – | – | 51.2%#3 | Epoch AI Benchmarking Hub | |
| Code2Video-AAnot in index | – | – | – | – | 1536#1 | – | Artificial Analysis | |
| AA-3Dnot in index | – | – | – | – | 1202#3 | – | Artificial Analysis |
Long context
| Benchmark | low | medium | high | xhigh | max | Source | Trend |
|---|---|---|---|---|---|---|---|
| AA-LCR v1.1 | 80.7%#74 | 84.3%#10 | 82.7%#40 | 84.7%#6 | 84.7%#6 | Artificial Analysis | |
| MLCRnot in index | 19.4%#54 | 22.2%#40 | 15.0%#81 | 25.0%#31 | 27.8%#22 | Artificial Analysis |
Composite
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | – | – | 168.4#3 | Epoch AI Benchmarking Hub | |
| LiveBench 2.0effort not stated | – | – | – | – | – | 83.4%#4 | LiveBench | |
| LiveBench 1.0not in index | – | – | – | 82.1%#5 | 83.2%#2 | – | LiveBench | |
| AA Intelligence Index v5.0not in index | 34.8#47 | 48.2#26 | 51.8#17 | 57.4#7 | 59.1#5 | – | Artificial Analysis | |
| AA Intelligence Index v4.3.2not in index | 42.3#56 | 51.2#15 | 53.6#6 | 56.0#3 | 57.6#1 | – | Artificial Analysis | |
| AA Progress Index v1not in index | 325#41 | 340.3#21 | 344#12 | 351.3#1 | 350#5 | – | Artificial Analysis | |
| Vals Indexnot in indexeffort not stated | – | – | – | – | – | 70.1#4 | Vals AI | |
| Vals Finance Indexnot in indexeffort not stated | – | – | – | – | – | 65.3%#3 | Vals AI | |
| Vals RSI Indexnot in index | – | – | – | – | 37.3%#1 | – | Vals AI | |
| Vals Science Indexnot in indexeffort not stated | – | – | – | – | – | 58.6%#5 | Vals AI | |
| Vals Router Indexnot in indexeffort not stated | – | – | – | – | – | 64.2%#6 | Vals AI | |
| AA Cyber Indexnot in index | – | – | – | – | 28.7#16 | – | Artificial Analysis |
Safety & honesty
| Benchmark | max | not stated | Source | Trend |
|---|---|---|---|---|
| FORTRESSnot in index | 5.8%#78 | 13.2%#66 | Scale AI SEAL |
GameBench 2 Overall: 87.6. GameBench 2, best reasoning setting (XHigh): 94.8. Reference only, not part of the BenchLeader Index.
DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
- #1OTIS Mock AIME100.0% · of 287
- #1SciCode66.9% · of 228
- #1ProofBench100.0% · of 84
- #1Arena WebDev1818 · of 147
- #1Arena Agent20 · of 56
- #2MMMU-Pro87.7% · of 295
- #3FrontierMath Tiers 1–391.2% · of 121
- #3APEX-Agents73.5% · of 60
- #4FrontierCode 2.0 (AA)46.4% · of 122
- #5SimpleQA Verified72.2% · of 97
- #5HLE-Diamond (AA)67.9% · of 162
API pricing: 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 |
|---|---|---|---|---|---|---|
| Anthropic | 143 tok/s | 1.57 s | $8.00 | $40.00 | 1M | – |
| Google Vertex | 94 tok/s | 2.45 s | $4.40 | $22.00 | 1M | – |
| Azure | 86 tok/s | 2.98 s | $4.00 | $20.00 | 1M | – |
| Google Vertex | 86 tok/s | 2.65 s | $4.40 | $22.00 | 1M | – |
| Anthropic | 84 tok/s | 2.53 s | $4.00 | $20.00 | 1M | – |
| Google Vertex | 82 tok/s | 3.25 s | $4.00 | $20.00 | 1M | – |
| Claude Platform on AWS | 79 tok/s | 3.20 s | $4.00 | $20.00 | 1M | – |
| Amazon Bedrock | 76 tok/s | 4.20 s | $4.40 | $22.00 | 1M | – |
| Amazon Bedrock | 70 tok/s | 4.07 s | $4.40 | $22.00 | 1M | – |
| Amazon Bedrock | 63 tok/s | 4.29 s | $4.00 | $20.00 | 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 $0.200 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0076 | $0.0065 | 6.4 min |
| Summarize a 30-page report | 12,000 / 600 | $0.060 | $0.026 | 6.4 min |
| Code edit | 6,000 / 1,500 | $0.054 | $0.037 | 6.6 min |
| Agentic coding session | 60,000 / 4,000 | $0.320 | $0.149 | 6.9 min |
| Structured extraction | 2,000 / 200 | $0.012 | $0.0063 | 6.4 min |
More from Anthropic
Compare Claude Opus 5.5 with…
- Claude Opus 5.5 vs Claude Fable 5.2
- Claude Opus 5.5 vs Gemini 4 Carbon
- Claude Opus 5.5 vs GPT-6 Astra
- Claude Opus 5.5 vs GPT-6.1 Sol
- Claude Opus 5.5 vs Claude Fable 5.1
- Claude Opus 5.5 vs Claude Fable 5
- Claude Opus 5.5 vs Gemini 4 Argon
- Claude Opus 5.5 vs GPT-5.6 Sol
- Claude Opus 5.5 vs Claude Opus 5
- Claude Opus 5.5 vs Claude Sonnet 5.5
- Claude Opus 5.5 vs GPT-6.1 Terra
- Claude Opus 5.5 vs GPT-5.5
- Claude Opus 5.5 vs Muse Spark
- Claude Opus 5.5 vs Muse Wonder
- Claude Opus 5.5 vs GPT-5.4 Pro
- Claude Opus 5.5 vs GPT-5.4
- Claude Opus 5.5 vs Claude Opus 4.7
- Claude Opus 5.5 vs GPT-6 Sol
- Claude Opus 5.5 vs GPT-5.3-Codex
- Claude Opus 5.5 vs Claude Opus 4.6
- Claude Opus 5.5 vs Gemini 3.5 Flash
- Claude Opus 5.5 vs Qwen3.6 Max
- Claude Opus 5.5 vs Muse Spark 1.1
- Claude Opus 5.5 vs Gemini 3.7 Flash
- Claude Opus 5.5 vs Muse Wonder Full
- Claude Opus 5.5 vs Kimi K3
- Claude Opus 5.5 vs Gemini 3.8 Flash
- Claude Opus 5.5 vs Muse Spark 1.3
- Claude Opus 5.5 vs Muse Spark 1.2
- Claude Opus 5.5 vs Gemini 3.6 Flash
- Claude Opus 5.5 vs Kimi K3.1 Pro
- Claude Opus 5.5 vs o3
- Claude Opus 5.5 vs Gemini 3.1 Pro
- Claude Opus 5.5 vs GPT-5.6 Terra
- Claude Opus 5.5 vs Grok 4.6
- Claude Opus 5.5 vs Claude Opus 4.8
- Claude Opus 5.5 vs Kimi K3.1 Pro Together
- Claude Opus 5.5 vs Gemini 3 Pro
- Claude Opus 5.5 vs Qwen3.7
- Claude Opus 5.5 vs GLM-5
- Claude Opus 5.5 vs GPT-5.2
- Claude Opus 5.5 vs GPT-5 Pro
- Claude Opus 5.5 vs Grok 4.5
- Claude Opus 5.5 vs Kimi K2.6
- Claude Opus 5.5 vs Claude Opus 4.5
- Claude Opus 5.5 vs GLM 5.2
- Claude Opus 5.5 vs Claude Sonnet 5
- Claude Opus 5.5 vs Qwen3.6 Plus
- Claude Opus 5.5 vs DeepSeek V4 Pro
- Claude Opus 5.5 vs Mimo v2 Pro
- Claude Opus 5.5 vs GLM 5.3
- Claude Opus 5.5 vs Qwen3.8 Max
- Claude Opus 5.5 vs DeepSeek V4.1 Flash 1017
- Claude Opus 5.5 vs Gemini 3 Flash
- Claude Opus 5.5 vs Kimi K2.5
- Claude Opus 5.5 vs Mimo v2 Omni
- Claude Opus 5.5 vs GPT-5-Codex
- Claude Opus 5.5 vs Muse Spark Open 816B A42B
- Claude Opus 5.5 vs Dola Seed 2.0 Pro
See also
Embed or cite
Show where Claude Opus 5.5 ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page. To see ranks like this on OpenRouter and Hugging Face model pages, get the Chrome extension.
[](https://www.benchleader.com/models/claude-opus-5-5)Cite this
The ranking changes daily, so a reference carries the data date. APA style:
BenchLeader. (2026, November 9). Claude Opus 5.5 on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 9, 2026, from https://www.benchleader.com/models/claude-opus-5-5
BibTeX:
@misc{benchleader_claude_opus_5_5_20261109,
author = {{BenchLeader}},
title = {{Claude Opus 5.5 on the BenchLeader Index (method v1.4)}},
year = {2026},
month = nov,
howpublished = {\url{https://www.benchleader.com/models/claude-opus-5-5}},
note = {Data as of 2026-11-09}
}Every badge style, the embeddable top-10 widget and how to cite the Index
Questions people ask
- What are Claude Opus 5.5's benchmark scores?
- As of 9 Nov 2026, Claude Opus 5.5 (max effort) scores 68.9 ±4.6 on the BenchLeader Index, top 10, strongest in coding (80) and weakest in agents & tools (63). That rests on independent benchmark results only, and every score on this page links to its publisher.
- How does Claude Opus 5.5 rank?
- Claude Opus 5.5 (max effort) is #2 of 599 ranked configurations on 9 Nov 2026 (top 10). 30 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 69.4.
- How much does Claude Opus 5.5 cost per 1M tokens?
- As of 9 Nov 2026, Claude Opus 5.5 costs $4.00 per 1M input tokens and $20.00 per 1M output tokens, $8.00 blended (three input tokens per output token).
- Is Claude Opus 5.5 better than Gemini 4 Carbon?
- As of 9 Nov 2026, Claude Opus 5.5 (max) and Gemini 4 Carbon (high) are neck and neck on quality (68.9 vs 68.5, inside the ±5.5 margin of error) and cost about the same, so speed decides it: Claude Opus 5.5 (max) streams 1.5× faster. The head-to-head page has the benchmark-by-benchmark detail.
- When was Claude Opus 5.5 released?
- Anthropic released Claude Opus 5.5 on 22 Sep 2026. BenchLeader has results for it at 6 reasoning-effort settings.
Data as of 9 Nov 2026. Compare these configurations.
Cite as: BenchLeader, “Claude Opus 5.5: benchmarks, pricing, speed and rank”, data as of 9 Nov 2026, https://www.benchleader.com/models/claude-opus-5-5.