AnthropicClaude Opus 4.6
Claude Opus 4.6 is an Anthropic proprietary reasoning model, released 5 Feb 2026. Its best configuration (high reasoning effort) ranks #76 of 775 on the BenchLeader Index at 62.9 ±2.4, in the upper half. The ± is the point: 152 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 human preference (70) and lowest in coding (63). At $10.00 per million tokens blended it is among the most expensive ranked models. Output speed of 40 tokens per second puts it in the slowest quarter, with a first token in 1.2 s. It has been measured at 7 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 19 Oct 2026.
- Blended price
- $10.00/M
- $5.00 in · $25.00 out
- Output speed
- 40 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 1.21 s
- Context
- 1M
- Full answer
- –
- Cost per run
- –
- Released
- 5 Feb 2026
- Overall index63
- Reasoning66
- Coding63
- Maths64
- Human preference70
- Multimodal67
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 5.5max | 22 Sept 2026 | 72.7 | #1 |
| Claude Opus 5max | 24 Jul 2026 | 68.9 | #15 |
| Claude Opus 4.8max | 28 May 2026 | 63.4 | #64 |
| Claude Opus 4.7 | 16 Apr 2026 | 63.4 | #63 |
| Claude Opus 4.6highthis page | 5 Feb 2026 | 62.9 | #76 |
| Claude Opus 4.5thinking | 24 Nov 2025 | 60.0 | #119 |
| Claude Opus 4.1thinking | 5 Aug 2025 | 56.5 | #199 |
| Claude Opus 4thinking | 22 May 2025 | 55.1 | #230 |
| Claude 3 Opus | 4 Mar 2024 | 39.2 | #681 |
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 |
|---|---|---|---|---|---|---|
| no reasoning | 56.6 | #195 | 43 tok/s | 1.99 s | $0.0095 | Agents & tools 76 · Composite 59 · Instruction following 49 · Knowledge 63 · Long context 58 · Multimodal 56 · Reasoning 46 |
| low | – | – | 40 tok/s | 1.21 s | $0.0095 | Reasoning 61 |
| medium | – | – | 40 tok/s | 1.21 s | $0.0095 | Reasoning 63 |
| highbest | 62.9 | #76 | 40 tok/s | 1.21 s | $0.0095 | Coding 63 · Human preference 70 · Maths 64 · Multimodal 67 · Reasoning 66 |
| max | 57.4 | #177 | 48 tok/s | 22 s | $0.0095 | Agents & tools 58 · Composite 65 · Instruction following 42 · Knowledge 63 · Long context 64 · Maths 57 · Multimodal 58 · Reasoning 61 |
| thinking | 62.5 | #84 | 40 tok/s | 1.21 s | $0.0095 | Coding 64 · Knowledge 62 · Maths 65 · Reasoning 76 |
| not stated | 62.7 | #81 | 40 tok/s | 1.21 s | $0.0095 | Agents & tools 67 · Coding 60 · Human preference 64 · Maths 68 · Multimodal 66 · Reasoning 62 |
How its index has moved
8 Sept 2026 to 21 Oct 2026- high
- not stated
- max
- no reasoning
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 | no reasoning | low | medium | high | max | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | – | – | 88.4%#59 | – | 90.5%#41 | Epoch AI Benchmarking Hub | |
| Humanity's Last Exam | – | – | – | – | 34.4%#11 | – | 19.0%#24 | Scale AI / CAIS | |
| SimpleBencheffort not stated | – | – | – | – | – | – | 67.6%#16 | SimpleBench | |
| Arena Hard Prompts | – | – | – | 1531#3 | – | – | 1527#5 | Arena (LMArena) | |
| LiveBench 1.0 Reasoningnot in index | – | – | – | 88.7%#21 | – | – | – | LiveBench | |
| GPQA Diamond (AA)not in index | 84.0%#148 | – | – | – | 89.6%#71 | – | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 19.1%#219 | – | – | – | 39.9%#84 | – | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | – | – | – | – | – | 89.7%#28 | – | Vals AI | |
| Kagi LLM Benchmark | – | – | – | – | – | 83.6%#5 | 72.4%#23 | Kagi LLM Benchmark | |
| ARC-AGI-1 | – | 86.0%#99 | 92.0%#56 | 94.0%#43 | 93.0%#48 | – | – | ARC Prize | |
| ARC-AGI-2 | – | 64.6%#71 | 66.3%#67 | 69.2%#57 | 68.8%#59 | – | – | ARC Prize | |
| ARC-AGI-3 | – | – | – | – | 0.5%#42 | – | – | ARC Prize | |
| CritPt | 2.8%#185 | – | – | – | 12.6%#105 | – | – | Artificial Analysis | |
| Chess Puzzlesnot in index | – | – | – | – | 21.0%#87 | – | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | 7.0%#122 | – | – | 25.0%#46 | – | 15.0%#90 | Epoch AI Benchmarking Hub | |
| CL-benchnot in indexeffort not stated | – | – | – | – | – | – | 20.7%#7 | Epoch AI Benchmarking Hub | |
| CL-bench Lifenot in index | – | – | – | 17.0%#5 | – | – | 13.6%#8 | Epoch AI Benchmarking Hub | |
| LMCAnot in index | – | – | – | – | 55.8%#44 | – | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | – | – | – | – | 91.2%#73 | – | – | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in indexeffort not stated | – | – | – | – | – | – | 63.4%#40 | ForecastBench |
Coding
Agents & tools
| Benchmark | no reasoning | low | medium | high | max | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Terminal-Bencheffort not stated | – | – | – | – | – | – | 79.8%#5 | Terminal-Bench | |
| Cybencheffort not stated | – | – | – | – | – | – | 93.0%#1 | Cybench | |
| Remote Labor Indexeffort not stated | – | – | – | – | – | – | 4.2%#9 | Scale AI / CAIS | |
| APEX-Agents | – | – | – | – | 46.3%#35 | – | – | Mercor | |
| LiveBench Agentic Codingnot in index | – | – | – | 49.0%#46 | – | – | – | LiveBench | |
| Terminal-Bench Hard | 48.5%#26 | – | – | – | 46.2%#30 | – | – | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 84.8%#96 | – | – | – | 92.1%#52 | – | – | Artificial Analysis | |
| MCP Atlas | – | – | – | – | 76.8%#16 | – | – | Scale AI SEAL | |
| HiL-Bencheffort not stated | – | – | – | – | – | – | 38.3%#19 | Scale AI SEAL | |
| τ³-bench Bankingnot in index | – | – | – | – | 27.3%#14 | – | – | τ²-bench | |
| APEX-Agents (AA)not in index | – | – | – | – | 33.0%#10 | – | – | Artificial Analysis | |
| Terminal-Bench 2.0 (Vals)not in index | – | – | – | – | – | 58.4%#10 | – | Vals AI | |
| DeepResearch Benchnot in index | – | 51.4%#8 | 53.2%#6 | 55.3%#1 | – | – | – | DeepResearch Bench | |
| METR Time Horizonsnot in indexeffort not stated | – | – | – | – | – | – | 78.9%#2 | METR | |
| GBAEvalnot in indexeffort not stated | – | – | – | – | – | – | 44.1%#11 | Epoch AI Benchmarking Hub | |
| Vending-Bench 2not in indexeffort not stated | – | – | – | – | – | – | 8017.6#14 | Andon Labs |
Maths
| Benchmark | high | max | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | 66.0%#33 | – | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | 26.8%#42 | – | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | 91.1%#69 | – | 94.4%#53 | Epoch AI Benchmarking Hub | |
| ProofBench | – | 50.0%#30 | – | – | Vals AI | |
| LiveBench Mathematicsnot in index | 89.3%#39 | – | – | – | LiveBench | |
| AIME (Vals) | – | – | 95.6%#8 | – | Vals AI | |
| AIME 2026 | 96.7%#6 | – | – | – | MathArena | |
| HMMT February 2026 | 96.2%#5 | – | – | – | MathArena | |
| USAMO 2026not in index | 47.0%#6 | – | – | – | MathArena | |
| MathArena Apexpossible contamination | 34.5%#8 | – | – | – | MathArena | |
| Arena Maths | 1518#6 | – | – | 1505#10 | Arena (LMArena) |
Knowledge
| Benchmark | no reasoning | high | max | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | 47.0%#35 | – | – | Epoch AI Benchmarking Hub | |
| LiveBench 1.0 Data Analysisnot in index | – | 69.9%#53 | – | – | – | LiveBench | |
| AA-Omniscience | 2.4#118 | – | 13.7#87 | – | – | Artificial Analysis | |
| MMLU-Pro | – | – | – | 89.1%#15 | – | Vals AI | |
| LegalBench | – | – | – | 85.3%#22 | – | Vals AI | |
| CorpFin | – | – | – | 67.0%#13 | – | Vals AI | |
| TaxEval | – | – | – | 76.0%#8 | – | Vals AI | |
| MedQA | – | – | – | 95.4%#12 | – | Vals AI | |
| PRBench Finance | 53.3%#5 | – | – | – | – | Scale AI SEAL | |
| PRBench Legal | 52.3%#7 | – | – | – | – | Scale AI SEAL | |
| MultiNRCpossible contamination | 48.3%#13 | – | 57.1%#8 | – | – | Scale AI SEAL | |
| CaseLaw v2not in index | – | – | – | 62.1%#20 | – | Vals AI | |
| MedCodenot in index | – | – | – | 49.1%#26 | 48.2%#30 | Vals AI | |
| MedScribenot in index | – | – | – | 86.1%#24 | 86.7%#21 | Vals AI | |
| DrugDiscoveryBenchnot in index | – | – | 27.7%#17 | – | – | Scale AI SEAL | |
| EBR-benchnot in index | – | – | 12.7%#20 | – | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 45.8%#83 | – | 47.0%#77 | – | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 19.9%#278 | – | 37.2%#176 | – | – | Artificial Analysis | |
| Global-MMLU-Lite (AA)not in index | – | – | 92.2%#4 | – | – | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | high | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| LiveBench Languagenot in index | – | 83.3%#20 | – | – | LiveBench | |
| LiveBench Instruction Followingnot in index | – | 63.3%#50 | – | – | LiveBench | |
| IFBench | 44.6%#207 | – | 53.1%#156 | – | Artificial Analysis | |
| MultiChallenge | 56.0%#19 | – | 37.1%#30 | – | Scale AI SEAL | |
| TutorBench | 53.5%#10 | – | 53.7%#8 | – | Scale AI SEAL | |
| Arena Instruction Followingnot in index | – | 1512#3 | – | 1499#6 | Arena (LMArena) |
Human preference
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Text | 1503#5 | 1497#8 | Arena (LMArena) | |
| EQ-Bench 4effort not stated | – | 1223#12 | EQ-Bench | |
| Arena Creative Writingnot in index | 1500#4 | 1478#13 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1517#4 | 1512#8 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1522#3 | 1516#5 | Arena (LMArena) |
Multimodal
| Benchmark | no reasoning | high | max | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| Arena Vision | – | 1316#6 | – | – | 1312#11 | Arena (LMArena) | |
| MMMU-Pro | 72.5%#131 | – | 75.4%#98 | – | – | Artificial Analysis | |
| VISTA | 45.5%#25 | – | 46.1%#22 | – | – | Scale AI SEAL | |
| MMMU-Pro (Vals)not in index | – | – | – | 83.9%#29 | – | Vals AI | |
| MortgageTaxnot in index | – | – | – | 68.5%#15 | – | Vals AI | |
| SAGEnot in index | – | – | – | 51.6%#12 | – | Vals AI | |
| VTBnot in index | – | – | – | 27.5%#4 | – | Scale AI SEAL |
Long context
| Benchmark | no reasoning | high | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| AA-LCR | 67.0%#240 | – | 78.0%#120 | – | Artificial Analysis | |
| Arena Documentnot in index | – | 1495#2 | – | 1494#4 | Arena (LMArena) |
Composite
| Benchmark | no reasoning | high | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | 155.7#33 | Epoch AI Benchmarking Hub | |
| LiveBench 1.0not in index | – | 74.5%#41 | – | – | LiveBench | |
| AA Intelligence Index v4.3.2 | 26.4#152 | – | 31.9#112 | – | Artificial Analysis |
Safety & honesty
| Benchmark | no reasoning | max | Source | Trend |
|---|---|---|---|---|
| FORTRESSnot in index | 20.5%#38 | 13.0%#60 | Scale AI SEAL | |
| MASKnot in indexpossible contamination | 96.3%#1 | 85.4%#18 | Scale AI SEAL |
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 |
|---|---|---|---|---|---|---|
| Claude Platform on AWS | 39 tok/s | 1.21 s | $5.00 | $25.00 | 1M | – |
| Amazon Bedrock | 38 tok/s | 1.72 s | $5.00 | $25.00 | 1M | – |
| Google Vertex | 37 tok/s | 1.78 s | $5.00 | $25.00 | 1M | – |
| Anthropic | 32 tok/s | 1.98 s | $5.00 | $25.00 | 1M | – |
Price history
Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.
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 $0.500 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0095 | $0.0081 | 8.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.075 | $0.035 | 16.2 s |
| Code edit | 6,000 / 1,500 | $0.068 | $0.047 | 38.7 s |
| Agentic coding session | 60,000 / 4,000 | $0.400 | $0.198 | 1.7 min |
| Structured extraction | 2,000 / 200 | $0.015 | $0.0083 | 6.2 s |
More from Anthropic
Compare Claude Opus 4.6 with…
- Claude Opus 4.6 vs Claude Opus 5.5
- Claude Opus 4.6 vs Gemini 4 Argon
- Claude Opus 4.6 vs Muse Wonder Full
- Claude Opus 4.6 vs GPT-6 Astra
- Claude Opus 4.6 vs Claude Fable 5.1
- Claude Opus 4.6 vs GPT-6.1 Sol
- Claude Opus 4.6 vs Claude Sonnet 5.5
- Claude Opus 4.6 vs Claude Fable 5
- Claude Opus 4.6 vs Claude Opus 5
- Claude Opus 4.6 vs GPT-5.6 Sol
- Claude Opus 4.6 vs Muse Wonder
- Claude Opus 4.6 vs Muse Spark 1.3
- Claude Opus 4.6 vs GPT-6 Sol
- Claude Opus 4.6 vs GPT-5.5
- Claude Opus 4.6 vs GPT-5.5 Pro
- Claude Opus 4.6 vs Kimi K3
- Claude Opus 4.6 vs GPT-5.4
- Claude Opus 4.6 vs Gemini 3.8 Flash
- Claude Opus 4.6 vs Muse Spark
- Claude Opus 4.6 vs GPT-5.6 Terra
- Claude Opus 4.6 vs MiMo-V2.6-Pro
- Claude Opus 4.6 vs Grok 4.6
- Claude Opus 4.6 vs Grok 4.7
- Claude Opus 4.6 vs GPT-5.3-Codex
- Claude Opus 4.6 vs GLM 5.3
- Claude Opus 4.6 vs Gemini 3.7 Flash
- Claude Opus 4.6 vs GPT-5.4 Pro
- Claude Opus 4.6 vs Claude Opus 4.7
- Claude Opus 4.6 vs Claude Opus 4.8
- Claude Opus 4.6 vs Qwen3.8 Max
- Claude Opus 4.6 vs Gemini 3.5 Flash
- Claude Opus 4.6 vs Muse Spark 1.2
- Claude Opus 4.6 vs Qwen3.8 2.4T A95B
- Claude Opus 4.6 vs DeepSeek V4.1 Flash 1017
- Claude Opus 4.6 vs Muse Spark 1.1
- Claude Opus 4.6 vs GLM 5.3 Flash
- Claude Opus 4.6 vs DeepSeek V4 Pro
- Claude Opus 4.6 vs GLM 5.2
- Claude Opus 4.6 vs Qwen3.6 Max
See also
Data as of 21 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Claude Opus 4.6: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/claude-opus-4-6, data as of 21 Oct 2026.