AnthropicClaude Opus 5
Reasoning effort
Claude Opus 5 is an Anthropic proprietary reasoning model, released 24 Jul 2026. Its best configuration (max reasoning effort) ranks #15 of 784 on the BenchLeader Index at 68.8 ±2.7, in the top 25. The ± is the point: 56 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 (86) and lowest in agents & tools (64). At $10.00 per million tokens blended it is among the most expensive ranked models. Output speed of 51 tokens per second puts it in the slowest quarter, with a first answer in 68.7 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 23 Oct 2026.
- Blended price
- $10.00/M
- $5.00 in · $25.00 out
- Output speed
- 51 tok/s
- measured by Artificial Analysis
- First answer
- 69 s
- first token 3.51 s
- Context
- 1M
- Full answer
- 78 s
- median, reasoning included
- Cost per run
- $5.86
- one full Intelligence Index run
- Released
- 24 Jul 2026
- Overall index69
- Reasoning74
- Coding70
- Agents & tools64
- Maths71
- Knowledge72
- Human preference69
- Multimodal68
- Long context65
- Composite86
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 | 72.6 | #1 |
| Claude Opus 5maxthis page | 24 Jul 2026 | 68.8 | #15 |
| Claude Opus 4.8max | 28 May 2026 | 63.3 | #65 |
| Claude Opus 4.7 | 16 Apr 2026 | 63.2 | #69 |
| Claude Opus 4.6high | 5 Feb 2026 | 62.7 | #78 |
| Claude Opus 4.5thinking | 24 Nov 2025 | 59.9 | #120 |
| Claude Opus 4.1thinking | 5 Aug 2025 | 56.4 | #204 |
| Claude Opus 4thinking | 22 May 2025 | 55.0 | #235 |
| Claude 3 Opus | 4 Mar 2024 | 39.2 | #690 |
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 | 61.3 | #99 | 52 tok/s | 1.84 s | $0.0095 | Agents & tools 52 · Coding 51 · Composite 74 · Knowledge 74 · Long context 66 · Maths 64 · Multimodal 63 · Reasoning 71 |
| medium | 64.6 | #47 | 51 tok/s | 3.03 s | $0.0095 | Agents & tools 60 · Coding 55 · Composite 80 · Knowledge 76 · Long context 66 · Multimodal 65 · Reasoning 85 |
| high | 67.9 | #18 | 54 tok/s | 17 s | $0.0095 | Agents & tools 65 · Coding 69 · Composite 83 · Human preference 69 · Knowledge 77 · Long context 65 · Maths 71 · Multimodal 66 · Reasoning 72 |
| xhigh | 67.4 | #24 | 52 tok/s | 31 s | $0.0095 | Agents & tools 66 · Coding 61 · Composite 85 · Knowledge 77 · Long context 65 · Multimodal 67 · Reasoning 86 |
| maxbest | 68.8 | #15 | 51 tok/s | 69 s | $0.0095 | Agents & tools 64 · Coding 70 · Composite 86 · Human preference 69 · Knowledge 72 · Long context 65 · Maths 71 · Multimodal 68 · Reasoning 74 |
| not stated | 65.1 | #40 | 65 tok/s | 3.51 s | $0.0095 | Agents & tools 66 · Coding 68 · Human preference 75 · Knowledge 66 · Maths 66 · Reasoning 71 |
What more thinking costs
Turning the effort up buys index points and multiplies the bill. Here max costs 5.3× low for +7.5 on the index — 3.1 points per doubling of spend. Compare that with other models.
How its index has moved
8 Sept 2026 to 25 Oct 2026- max
- high
- xhigh
- 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 | 87.9%#65 | – | – | – | 93.9%#15 | 92.9%#23 | Epoch AI Benchmarking Hub | |
| SimpleBencheffort not stated | – | – | – | – | – | 80.6%#2 | SimpleBench | |
| Arena Hard Prompts | – | – | 1516#13 | – | 1515#14 | – | Arena (LMArena) | |
| LiveBench 1.0 Reasoningnot in index | – | – | – | – | 91.2%#8 | – | LiveBench | |
| GPQA Diamond (AA)not in index | 88.9%#85 | 91.9%#44 | 93.7%#11 | 93.7%#11 | 93.2%#22 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 43.4%#59 | 51.3%#24 | 52.8%#19 | 54.4%#14 | 54.9%#10 | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in indexeffort not stated | – | – | – | – | – | 93.4%#7 | Vals AI | |
| ARC-AGI-1 | – | – | 97.5%#12 | – | 97.5%#12 | – | ARC Prize | |
| ARC-AGI-2 | – | – | 88.3%#21 | – | 90.4%#13 | – | ARC Prize | |
| ARC-AGI-3 | – | – | 30.2%#18 | – | – | – | ARC Prize | |
| CritPt | 23.1%#53 | 26.9%#36 | 28.3%#26 | 27.7%#29 | 29.1%#20 | – | Artificial Analysis | |
| MysteryMechanismnot in indexeffort not stated | – | – | – | – | – | 37.4%#7 | Vals AI | |
| Chess Puzzlesnot in index | 27.0%#72 | – | – | – | 43.0%#34 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | 59.0%#6 | 37.0%#19 | Epoch AI Benchmarking Hub | |
| LMCAnot in index | 62.6%#28 | 62.9%#23 | 63.7%#20 | 64.5%#15 | 63.3%#22 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 93.1%#67 | 94.9%#46 | 97.9%#3 | 97.9%#3 | 97.6%#5 | – | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | – | – | – | – | 66.5%#2 | – | ForecastBench | |
| BTF-3not in index | – | – | – | 12.0%#13 | – | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SciCode | 48.0%#122 | 50.7%#102 | 54.3%#62 | 55.0%#52 | 56.4%#39 | – | SciCode | |
| WeirdML | – | – | 91.6%#8 | – | 91.8%#7 | 86.3%#13 | WeirdML | |
| FrontierCode | – | – | – | – | 53.4%#3 | – | Cognition | |
| Arena Coding | – | – | 1534#16 | – | 1528#23 | – | Arena (LMArena) | |
| Arena WebDev | – | – | 1659#14 | – | 1691#9 | – | Arena (LMArena) | |
| LiveBench 1.0 Codingnot in index | – | – | – | – | 81.5%#14 | – | LiveBench | |
| SciCode (AA)not in index | 49.2%#118 | 51.5%#96 | 55.4%#52 | 55.7%#48 | 56.4%#40 | – | Artificial Analysis | |
| LiveCodeBencheffort not stated | – | – | – | – | – | 89.0%#4 | Vals AI | |
| IOIeffort not stated | – | – | – | – | – | 84.3%#8 | Vals AI | |
| SWE-bench (Vals)not in indexeffort not stated | – | – | – | – | – | 97.0%#1 | Vals AI | |
| Code Migrationnot in indexeffort not stated | – | – | – | – | – | 57.5%#8 | Vals AI | |
| ProgramBenchnot in indexeffort not stated | – | – | – | – | – | 3.0%#5 | Vals AI | |
| Vibe Code Bench 1-100not in indexeffort not stated | – | – | – | – | – | 28.5%#3 | Vals AI | |
| Vibe Code Bench v1.1not in indexeffort not stated | – | – | – | – | – | 88.4%#9 | Vals AI | |
| SWE Atlas: Codebase QnAnot in index | – | – | – | 63.2%#1 | – | – | Scale AI SEAL | |
| SWE Atlas: Test Writingnot in index | – | – | – | 62.2%#2 | – | – | Scale AI SEAL | |
| DeepSWE v1.1not in index | 58.1%#35 | 68.9%#17 | 72.8%#7 | 73.2%#6 | 73.7%#3 | – | Epoch AI Benchmarking Hub | |
| CursorBenchnot in index | 40.7%#38 | 43.3%#29 | 44.7%#25 | 46.1%#21 | 46.6%#19 | – | Cursor | |
| ALE-Benchnot in index | – | – | 2164.6#5 | – | – | – | Epoch AI Benchmarking Hub | |
| FrontierSWEnot in index | – | – | – | – | 52.0%#6 | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 26.3%#51 | 34.3%#37 | 46.0%#24 | 46.5%#23 | 49.0%#21 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 76.4%#59 | 86.1%#21 | 87.6%#18 | 88.0%#12 | 89.1%#7 | – | Artificial Analysis | |
| Startrise Frontendnot in indexeffort not stated | – | – | – | – | – | 82.3%#1 | Startrise |
Agents & tools
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Terminal-Bench | 34.9%#55 | 44.9%#41 | 50.3%#33 | 53.9%#27 | 51.8%#31 | – | Terminal-Bench | |
| OSWorld-Verified 2.0 | 22.3%#6 | 25.3%#5 | 29.0%#3 | 30.2%#2 | 31.4%#1 | – | OSWorld | |
| APEX-Agents | – | – | – | – | 65.8%#6 | – | Mercor | |
| Arena Agent | – | – | – | – | 8.2#8 | – | Arena (LMArena) | |
| LiveBench Agentic Codingnot in index | – | – | – | – | 65.2%#5 | – | LiveBench | |
| Terminal-Bench 2.1 (Vals)effort not stated | – | – | – | – | – | 84.6%#5 | Vals AI | |
| MCP Atlas | – | – | – | 85.8%#3 | – | – | Scale AI SEAL | |
| HiL-Bencheffort not stated | – | – | – | – | – | 57.0%#11 | Scale AI SEAL | |
| τ³-bench Bankingnot in index | – | – | – | – | 48.7%#2 | – | τ²-bench | |
| τ³-Banking (AA) | 30.3%#65 | 38.6%#36 | 44.7%#16 | 43.3%#19 | 42.1%#23 | – | Artificial Analysis | |
| Analyst Agent (AA)not in index | – | – | – | – | 53.8%#6 | – | Artificial Analysis | |
| CUA-benchnot in index | – | – | – | – | 9.0%#4 | – | Vals AI | |
| CyberBenchnot in indexeffort not stated | – | – | – | – | – | 65.4%#30 | Vals AI | |
| Finance Agent v2not in indexeffort not stated | – | – | – | – | – | 58.6%#10 | Vals AI | |
| Harvey's Legal Agent Benchmark v1not in indexeffort not stated | – | – | – | – | – | 6.7%#30 | Vals AI | |
| Legal Research Benchnot in indexeffort not stated | – | – | – | – | – | 55.3%#1 | Vals AI | |
| SkillsBenchnot in indexeffort not stated | – | – | – | – | – | 60.4%#8 | Vals AI | |
| SREBenchnot in indexeffort not stated | – | – | – | – | – | 12.2%#11 | Vals AI | |
| Tax Agent Benchnot in indexeffort not stated | – | – | – | – | – | 45.5%#4 | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in indexeffort not stated | – | – | – | – | – | 53.5%#9 | Vals AI | |
| Terminal-Bench Sciencenot in indexeffort not stated | – | – | – | – | – | 27.1%#9 | Vals AI | |
| Time Horizon Index: KSPnot in indexeffort not stated | – | – | – | – | – | 18.8%#6 | Vals AI | |
| Arena Searchnot in index | – | – | 1214#10 | – | – | – | Arena (LMArena) | |
| BALROGnot in index | – | – | – | – | 63.4%#2 | – | BALROG | |
| PostTrainBenchnot in indexeffort not stated | – | – | – | – | – | 35.0%#3 | Epoch AI Benchmarking Hub | |
| GBAEvalnot in indexeffort not stated | – | – | – | – | – | 79.6%#1 | Epoch AI Benchmarking Hub | |
| Vending-Bench 2not in indexeffort not stated | – | – | – | – | – | 11181.9#4 | Andon Labs | |
| AutomationBenchnot in index | 51.8%#75 | 54.3%#62 | 53.6%#66 | 53.2%#68 | 56.6%#53 | – | Artificial Analysis | |
| GDP.pdf (AA)not in index | 17.2%#83 | 20.0%#65 | 19.6%#68 | 21.0%#56 | 21.6%#53 | – | Artificial Analysis | |
| EnterpriseOps-Gymnot in index | – | – | – | – | 47.5%#7 | – | Artificial Analysis | |
| AA-Briefcase v1.1not in index | – | – | – | – | 1657#7 | – | Artificial Analysis | |
| Terminal-Bench-Science 0.1 (AA)not in index | – | – | – | – | 28.6%#18 | – | Artificial Analysis | |
| DeepSec-Bench (AA) | – | – | – | – | 25.9%#8 | – | Artificial Analysis | |
| FACTS Searchnot in indexeffort not stated | – | – | – | – | – | 85.3%#6 |
Maths
| Benchmark | low | high | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | – | 85.6%#12 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | – | 73.2%#18 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 93.3%#59 | – | 98.9%#19 | 97.8%#31 | Epoch AI Benchmarking Hub | |
| ProofBench | – | – | 99.0%#4 | – | Vals AI | |
| LiveBench Mathematicsnot in index | – | – | 95.7%#15 | – | LiveBench | |
| Arena Maths | – | 1521#5 | 1517#6 | – | Arena (LMArena) |
Knowledge
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | – | – | 59.9%#17 | – | Epoch AI Benchmarking Hub | |
| LiveBench 1.0 Data Analysisnot in index | – | – | – | – | 74.5%#37 | – | LiveBench | |
| AA-Omniscience | 28.6#39 | 31.0#29 | 33.7#25 | 35.4#23 | 37.1#22 | – | Artificial Analysis | |
| MMLU-Proeffort not stated | – | – | – | – | – | 91.6%#2 | Vals AI | |
| LegalBencheffort not stated | – | – | – | – | – | 87.0%#9 | Vals AI | |
| CorpFineffort not stated | – | – | – | – | – | 73.2%#1 | Vals AI | |
| TaxEvaleffort not stated | – | – | – | – | – | 75.1%#22 | Vals AI | |
| BioMysteryBenchnot in indexeffort not stated | – | – | – | – | – | 79.3%#3 | Vals AI | |
| Excel Modeling Benchmarknot in indexeffort not stated | – | – | – | – | – | 73.6%#6 | Vals AI | |
| MedCodenot in indexeffort not stated | – | – | – | – | – | 63.6%#1 | Vals AI | |
| MedScribenot in indexeffort not stated | – | – | – | – | – | 91.0%#4 | Vals AI | |
| Public Benefits Bench v1.1not in indexeffort not stated | – | – | – | – | – | 76.9%#1 | Vals AI | |
| DrugDiscoveryBenchnot in index | – | – | – | – | 53.7%#5 | – | Scale AI SEAL | |
| EBR-benchnot in index | – | – | – | – | 45.7%#7 | – | Epoch AI Benchmarking Hub | |
| GDP.pdfnot in index | – | – | – | – | 24.0%#19 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 56.0%#35 | 57.1%#31 | 58.9%#24 | 59.5%#22 | 60.9%#15 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 37.8%#174 | 39.3%#162 | 38.8%#167 | 40.5%#158 | 39.2%#163 | – | Artificial Analysis |
Instruction following
| Benchmark | high | max | Source | Trend |
|---|---|---|---|---|
| LiveBench Languagenot in index | – | 88.7%#5 | LiveBench | |
| LiveBench Instruction Followingnot in index | – | 63.8%#49 | LiveBench | |
| Arena Instruction Followingnot in index | 1495#9 | 1495#10 | Arena (LMArena) |
Human preference
| Benchmark | high | max | not stated | Source | Trend |
|---|---|---|---|---|---|
| Arena Text | 1491#14 | 1491#13 | – | Arena (LMArena) | |
| EQ-Bench 4effort not stated | – | – | 1360#1 | EQ-Bench | |
| Arena Creative Writingnot in index | 1471#16 | 1474#14 | – | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1486#28 | 1487#27 | – | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1502#13 | 1503#11 | – | Arena (LMArena) |
Multimodal
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Arena Vision | – | – | 1320#3 | – | – | – | Arena (LMArena) | |
| MMMU-Pro | 79.8%#56 | 81.6%#38 | 82.4%#33 | 84.0%#22 | 84.7%#15 | – | Artificial Analysis | |
| MMMU-Pro (Vals)not in indexeffort not stated | – | – | – | – | – | 89.9%#2 | Vals AI | |
| MortgageTaxnot in indexeffort not stated | – | – | – | – | – | 72.1%#1 | Vals AI | |
| SAGEnot in indexeffort not stated | – | – | – | – | – | 49.4%#21 | Vals AI | |
| Blueprint-Bench 2not in indexeffort not stated | – | – | – | – | – | 30.4%#18 | Epoch AI Benchmarking Hub |
Long context
| Benchmark | low | medium | high | xhigh | max | Source | Trend |
|---|---|---|---|---|---|---|---|
| AA-LCR | 81.3%#56 | 82.0%#47 | 79.0%#106 | 80.3%#71 | 79.3%#98 | Artificial Analysis | |
| Arena Documentnot in index | – | – | 1490#7 | – | – | Arena (LMArena) | |
| MLCRnot in index | 13.9%#86 | 13.9%#86 | 11.7%#102 | 10.0%#114 | 11.1%#105 | Artificial Analysis |
Composite
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | – | – | 163.9#7 | Epoch AI Benchmarking Hub | |
| LiveBench 1.0not in index | – | – | – | – | 80.1%#13 | – | LiveBench | |
| AA Intelligence Index v4.3.2 | 39.4#70 | 44.8#39 | 48.1#25 | 49.7#21 | 50.8#19 | – | Artificial Analysis | |
| Vals RSI Indexnot in index | – | – | – | – | 33.0%#3 | – | Vals AI | |
| Vals Science Indexnot in indexeffort not stated | – | – | – | – | – | 47.9%#7 | Vals AI | |
| Vals Multimodal Indexnot in indexeffort not stated | – | – | – | – | – | 73.9%#2 | Vals AI |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FORTRESSnot in index | 16.8%#49 | 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 |
|---|---|---|---|---|---|---|
| Anthropic | 123 tok/s | 1.46 s | $10.00 | $50.00 | 1M | – |
| Azure | 74 tok/s | 2.51 s | $5.00 | $25.00 | 1M | – |
| Amazon Bedrock | 69 tok/s | 1.82 s | $5.50 | $27.50 | 1M | – |
| Claude Platform on AWS | 65 tok/s | 3.51 s | $5.00 | $25.00 | 1M | – |
| Google Vertex | 61 tok/s | 8.72 s | $5.00 | $25.00 | 1M | – |
| Google Vertex | 61 tok/s | 2.93 s | $5.50 | $27.50 | 1M | – |
| Anthropic | 57 tok/s | 2.99 s | $5.00 | $25.00 | 1M | – |
| Amazon Bedrock | 56 tok/s | 4.86 s | $5.00 | $25.00 | 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 $0.500 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0095 | $0.0081 | 1.2 min |
| Summarize a 30-page report | 12,000 / 600 | $0.075 | $0.035 | 1.3 min |
| Code edit | 6,000 / 1,500 | $0.068 | $0.047 | 1.6 min |
| Agentic coding session | 60,000 / 4,000 | $0.400 | $0.198 | 2.4 min |
| Structured extraction | 2,000 / 200 | $0.015 | $0.0083 | 1.2 min |
More from Anthropic
Compare Claude Opus 5 with…
- Claude Opus 5 vs Claude Opus 5.5
- Claude Opus 5 vs Gemini 4 Argon
- Claude Opus 5 vs Muse Wonder Full
- Claude Opus 5 vs Claude Fable 5.1
- Claude Opus 5 vs GPT-6 Astra
- Claude Opus 5 vs GPT-6.1 Sol
- Claude Opus 5 vs Claude Sonnet 5.5
- Claude Opus 5 vs Claude Fable 5
- Claude Opus 5 vs GPT-5.6 Sol
- Claude Opus 5 vs Muse Wonder
- Claude Opus 5 vs Muse Spark 1.3
- Claude Opus 5 vs Kimi K3.1 Pro
- Claude Opus 5 vs GPT-6 Sol
- Claude Opus 5 vs GPT-5.5
- Claude Opus 5 vs GPT-5.5 Pro
- Claude Opus 5 vs Kimi K3
- Claude Opus 5 vs GPT-5.4
- Claude Opus 5 vs Gemini 3.8 Flash
- Claude Opus 5 vs GPT-5.6 Terra
- Claude Opus 5 vs Muse Spark
- Claude Opus 5 vs Grok 4.6
- Claude Opus 5 vs DeepSeek V4.1 Flash 1017
- Claude Opus 5 vs Grok 4.7
- Claude Opus 5 vs MiMo-V2.6-Pro
- Claude Opus 5 vs GPT-5.3-Codex
- Claude Opus 5 vs GLM 5.3
- Claude Opus 5 vs Gemini 3.7 Flash
- Claude Opus 5 vs Claude Opus 4.8
- Claude Opus 5 vs GPT-5.4 Pro
- Claude Opus 5 vs Qwen3.8 Max
- Claude Opus 5 vs Claude Opus 4.7
- Claude Opus 5 vs Muse Spark 1.2
- Claude Opus 5 vs Gemini 3.5 Flash
- Claude Opus 5 vs Claude Opus 4.6
- Claude Opus 5 vs Muse Spark 1.1
- Claude Opus 5 vs GLM 5.2
- Claude Opus 5 vs GLM 5.3 Flash
- Claude Opus 5 vs Qwen3.6 Max
- Claude Opus 5 vs Gemini 3.6 Flash
- Claude Opus 5 vs Muse Spark Open
- Claude Opus 5 vs Gemini 3.1 Pro
- Claude Opus 5 vs MiniMax M3.1 Flash
- Claude Opus 5 vs Claude Haiku 5.5
- Claude Opus 5 vs Qwen3.8 2.4T A95B
- Claude Opus 5 vs DeepSeek V4 Pro
- Claude Opus 5 vs GPT-5.2
- Claude Opus 5 vs Qwen3.7
- Claude Opus 5 vs Gemini 3 Pro
- Claude Opus 5 vs Step 5 Preview
- Claude Opus 5 vs Qwen3.8-Flash-Next
- Claude Opus 5 vs Claude Sonnet 5
- Claude Opus 5 vs GPT-6 Luna
- Claude Opus 5 vs Grok 4.5
- Claude Opus 5 vs Claude Opus 4.5
- Claude Opus 5 vs GPT-5.6 Luna
- Claude Opus 5 vs GPT-5 Pro
- Claude Opus 5 vs MiMo-V2.6-Flash
- Claude Opus 5 vs DeepSeek V4 Pro 0424
- Claude Opus 5 vs o3
See also
Questions people ask
- What are Claude Opus 5's benchmark scores?
- As of 26 Oct 2026, Claude Opus 5 (max effort) scores 68.8 ±2.7 on the BenchLeader Index, top 25, strongest in composite (86) and weakest in agents & tools (64). That rests on 27 independent benchmark results, and every score on this page links to its publisher.
- How does Claude Opus 5 rank?
- Claude Opus 5 (max effort) is #15 of 784 ranked configurations on 26 Oct 2026 (top 25). 56 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Claude Opus 5 cost per 1M tokens?
- As of 26 Oct 2026, Claude Opus 5 costs $5.00 per 1M input tokens and $25.00 per 1M output tokens, $10.00 blended (three input tokens per output token).
- Is Claude Opus 5 better than Claude Fable 5?
- As of 26 Oct 2026, Claude Fable 5 (max) and Claude Opus 5 (max) are neck and neck on quality (69.3 vs 68.8 on the BenchLeader Index, inside the ±5.1 margin of error), and Claude Opus 5 (max) costs 2.0× less, which makes it the better buy for most workloads. The head-to-head page has the benchmark-by-benchmark detail.
- When was Claude Opus 5 released?
- Anthropic released Claude Opus 5 on 24 Jul 2026. BenchLeader has results for it at 6 reasoning-effort settings.
Data as of 26 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Claude Opus 5: benchmarks, pricing, speed and rank”, data as of 26 Oct 2026, https://www.benchleader.com/models/claude-opus-5.