AnthropicClaude Opus 4.5
Claude Opus 4.5 is an Anthropic proprietary reasoning model, released 24 Nov 2025. Its best configuration (thinking reasoning effort) ranks #119 of 785 on the BenchLeader Index at 59.9 ±2.8, in the upper half. The ± is the point: 211 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 agents & tools (75) and lowest in instruction following (54). At $10.00 per million tokens blended it is among the most expensive ranked models. Output speed of 60 tokens per second puts it slower than most, with a first answer in 18.8 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 13 Oct 2026.
- Blended price
- $10.00/M
- $5.00 in · $25.00 out
- Output speed
- 60 tok/s
- measured by Artificial Analysis
- First answer
- 19 s
- first token 1.43 s
- Context
- 200k
- Full answer
- 27 s
- median, reasoning included
- Cost per run
- –
- Released
- 24 Nov 2025
- Overall index60
- Reasoning54
- Coding61
- Agents & tools75
- Maths64
- Knowledge60
- Instruction following54
- Multimodal57
- Long context64
- Composite62
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 5max | 24 Jul 2026 | 68.8 | #15 |
| Claude Opus 4.8max | 28 May 2026 | 63.3 | #67 |
| Claude Opus 4.7 | 16 Apr 2026 | 63.3 | #66 |
| Claude Opus 4.6high | 5 Feb 2026 | 62.7 | #78 |
| Claude Opus 4.5thinkingthis page | 24 Nov 2025 | 59.9 | #119 |
| Claude Opus 4.1thinking | 5 Aug 2025 | 56.4 | #204 |
| Claude Opus 4thinking | 22 May 2025 | 55.0 | #236 |
| Claude 3 Opus | 4 Mar 2024 | 39.2 | #691 |
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 | 53.6 | #282 | 48 tok/s | 1.09 s | $0.0095 | Agents & tools 70 · Composite 56 · Instruction following 45 · Knowledge 60 · Long context 60 · Multimodal 54 · Reasoning 39 |
| low | – | – | 42 tok/s | 1.43 s | $0.0095 | |
| medium | – | – | 42 tok/s | 1.43 s | $0.0095 | Coding 65 |
| high | 59.2 | #136 | 42 tok/s | 1.43 s | $0.0095 | Agents & tools 54 · Coding 61 · Human preference 66 · Maths 65 · Reasoning 67 |
| thinkingbest | 59.9 | #119 | 60 tok/s | 19 s | $0.0095 | Agents & tools 75 · Coding 61 · Composite 62 · Instruction following 54 · Knowledge 60 · Long context 64 · Maths 64 · Multimodal 57 · Reasoning 54 |
| not stated | 57.9 | #166 | 42 tok/s | 1.43 s | $0.0095 | Agents & tools 70 · Coding 56 · Human preference 66 · Instruction following 46 · Knowledge 56 · Maths 53 · Multimodal 60 · Reasoning 61 |
How its index has moved
8 Sept 2026 to 21 Oct 2026- thinking
- high
- not stated
- 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 | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| GPQA Diamondeffort not stated | – | – | – | 86.0%#83 | Epoch AI Benchmarking Hub | |
| Humanity's Last Exameffort not stated | – | – | – | 25.2%#17 | Scale AI / CAIS | |
| SimpleBencheffort not stated | – | – | – | 62.0%#22 | SimpleBench | |
| Arena Hard Prompts | – | 1501#34 | – | 1498#37 | Arena (LMArena) | |
| LiveBench 1.0 Reasoningnot in index | – | 80.1%#52 | – | – | LiveBench | |
| GPQA Diamond (AA)not in index | 81.0%#185 | – | 86.6%#109 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 13.2%#273 | – | 30.1%#149 | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | – | – | 85.9%#43 | 79.5%#68 | Vals AI | |
| Kagi LLM Benchmark | – | – | 80.2%#8 | 70.7%#25 | Kagi LLM Benchmark | |
| ARC-AGI-1 | 40.0%#192 | – | 80.0%#120 | – | ARC Prize | |
| ARC-AGI-2 | 7.8%#165 | – | 37.6%#121 | – | ARC Prize | |
| CritPt | 0.3%#271 | – | 4.6%#161 | – | Artificial Analysis | |
| SciPredictnot in indexeffort not stated | – | – | – | 23.1%#2 | Scale AI SEAL | |
| Chess Puzzlesnot in indexeffort not stated | – | – | – | 14.0%#111 | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in indexeffort not stated | – | – | – | 22.0%#55 | Epoch AI Benchmarking Hub | |
| CL-benchnot in indexeffort not stated | – | – | – | 21.1%#4 | Epoch AI Benchmarking Hub | |
| LMCAnot in index | – | 44.5%#94 | – | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | – | 89.9%#88 | – | – | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in indexeffort not stated | – | – | – | 64.9%#17 | ForecastBench |
Coding
| Benchmark | medium | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| SWE-bench Verified (Epoch)effort not stated | – | – | – | 76.7%#9 | Epoch AI Benchmarking Hub | |
| WeirdMLeffort not stated | – | – | – | 63.7%#41 | WeirdML | |
| GSO-Bencheffort not stated | – | – | – | 26.5%#14 | GSO-Bench | |
| Arena Coding | – | 1530#20 | – | 1523#31 | Arena (LMArena) | |
| Arena WebDev | – | 1494#60 | – | 1470#68 | Arena (LMArena) | |
| LiveBench 1.0 Codingnot in index | – | 79.7%#23 | – | – | LiveBench | |
| LiveCodeBench | – | – | 83.7%#45 | 75.0%#78 | Vals AI | |
| SWE-bench (Vals)not in index | – | – | 76.4%#35 | – | Vals AI | |
| SWE-Bench Proeffort not stated | – | – | – | 45.9%#6 | Scale AI SEAL | |
| SWE-bench Verified (bash only) | 74.4%#5 | 76.8%#1 | – | – | SWE-bench | |
| SWE-bench Verified (any scaffold)not in indexeffort not stated | – | – | – | 79.2%#1 | SWE-bench | |
| Vibe Code Bench v1.1not in index | – | – | 20.6%#81 | – | Vals AI | |
| SWE-Bench Pro (private)not in indexeffort not stated | – | – | – | 45.9%#6 | Scale AI SEAL | |
| ALE-Benchnot in indexeffort not stated | – | – | – | 1025.4#55 | Epoch AI Benchmarking Hub | |
| AlgoTunenot in indexeffort not stated | – | – | – | 1.8#5 | AlgoTune |
Agents & tools
| Benchmark | no reasoning | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| Terminal-Bencheffort not stated | – | – | – | – | 63.1%#13 | Terminal-Bench | |
| GDPvaleffort not stated | – | – | – | – | 45.5%#2 | OpenAI | |
| Cybencheffort not stated | – | – | – | – | 82.0%#2 | Cybench | |
| Remote Labor Indexeffort not stated | – | – | – | – | 3.8%#10 | Scale AI / CAIS | |
| LiveBench Agentic Codingnot in index | – | – | 39.7%#62 | – | – | LiveBench | |
| Terminal-Bench Hard | 40.9%#53 | – | – | 47.0%#27 | – | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 86.3%#88 | – | – | 89.5%#67 | – | Artificial Analysis | |
| MCP Atlas | – | – | 69.8%#21 | – | – | Scale AI SEAL | |
| BFCL Overalleffort not stated | – | – | – | – | 77.5%#1 | Berkeley Function Calling Leaderboard | |
| τ²-bench | – | – | 85.3%#2 | – | – | τ²-bench | |
| τ³-bench Bankingnot in index | – | – | 24.7%#18 | – | – | τ²-bench | |
| Poker Agentnot in indexeffort not stated | – | – | – | – | 1033.4%#10 | Vals AI | |
| Terminal-Bench 2.0 (Vals)not in index | – | – | – | 53.9%#16 | 58.4%#10 | Vals AI | |
| BALROGnot in indexeffort not stated | – | – | – | – | 43.0%#11 | BALROG | |
| DeepResearch Benchnot in index | – | 53.7%#5 | 54.8%#3 | – | – | DeepResearch Bench | |
| METR Time Horizonsnot in indexeffort not stated | – | – | – | – | 75.0%#5 | METR | |
| Vending-Bench 2not in indexeffort not stated | – | – | – | – | 4967.1#34 | Andon Labs | |
| DeepSearchQAnot in index | – | – | – | 24.0%#10 | – |
Maths
| Benchmark | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| FrontierMath Tiers 1–3effort not stated | – | – | 34.4%#68 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4effort not stated | – | – | 4.9%#66 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIMEeffort not stated | – | – | 86.1%#94 | Epoch AI Benchmarking Hub | |
| ProofBencheffort not stated | – | – | 36.0%#39 | Vals AI | |
| LiveBench Mathematicsnot in index | 90.4%#35 | – | – | LiveBench | |
| AIME (Vals) | – | 95.4%#12 | 76.9%#50 | Vals AI | |
| MGSM | – | 95.2%#1 | 94.8%#2 | Vals AI | |
| Arena Maths | 1472#50 | – | 1463#61 | Arena (LMArena) |
Knowledge
| Benchmark | no reasoning | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| SimpleQA Verifiedeffort not stated | – | – | – | 45.7%#38 | Epoch AI Benchmarking Hub | |
| LiveBench 1.0 Data Analysisnot in index | – | 74.4%#38 | – | – | LiveBench | |
| AA-Omniscience | -4.1#156 | – | 14#86 | – | Artificial Analysis | |
| MMLU-Pro | – | – | 87.3%#31 | 85.6%#55 | Vals AI | |
| LegalBench | – | – | 84.6%#31 | 82.8%#63 | Vals AI | |
| CorpFin | – | – | 65.1%#34 | 61.3%#54 | Vals AI | |
| TaxEval | – | – | 74.9%#25 | 74.3%#37 | Vals AI | |
| MedQA | – | – | 95.9%#10 | 93.2%#24 | Vals AI | |
| PRBench Finance | – | – | 46.2%#20 | – | Scale AI SEAL | |
| PRBench Legal | – | – | 44.2%#23 | – | Scale AI SEAL | |
| MultiNRCpossible contamination | – | – | 48.6%#12 | 41.2%#18 | Scale AI SEAL | |
| CaseLaw v2not in index | – | – | 62.6%#18 | – | Vals AI | |
| MedCodenot in index | – | – | 49.2%#25 | 45.2%#38 | Vals AI | |
| MedScribenot in index | – | – | 85.3%#28 | 83.3%#45 | Vals AI | |
| EBR-benchnot in indexeffort not stated | – | – | – | 14.3%#18 | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 40.9%#117 | – | 46.6%#80 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 23.8%#254 | – | 39.0%#166 | – | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| LiveBench Languagenot in index | – | 81.3%#27 | – | – | LiveBench | |
| LiveBench Instruction Followingnot in index | – | 62.5%#53 | – | – | LiveBench | |
| IFBench | 43.0%#230 | – | 58.0%#134 | – | Artificial Analysis | |
| MultiChallenge | – | – | 59.0%#16 | – | Scale AI SEAL | |
| TutorBench | – | – | 51.2%#16 | 49.8%#18 | Scale AI SEAL | |
| Arena Instruction Followingnot in index | – | 1483#20 | – | 1474#29 | Arena (LMArena) |
Human preference
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Text | 1474#42 | 1470#48 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1469#18 | 1462#29 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1485#29 | 1484#31 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1495#21 | 1492#23 | Arena (LMArena) |
Multimodal
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| MMMU-Pro | 71.2%#138 | 74.0%#116 | – | Artificial Analysis | |
| VISTA | – | 46.4%#21 | 45.3%#27 | Scale AI SEAL | |
| MMMU (validation)effort not stated | – | – | 80.7%#5 | MMMU | |
| MMMU-Pro (official)not in indexeffort not stated | – | – | 73.9%#8 | MMMU | |
| MMMU-Pro (Vals)not in index | – | 83.0%#36 | 81.1%#42 | Vals AI | |
| MortgageTaxnot in index | – | 67.7%#23 | 68.7%#12 | Vals AI | |
| SAGEnot in index | – | 52.1%#8 | 45.0%#42 | Vals AI | |
| GeoBenchnot in indexeffort not stated | – | – | 75.0%#9 | GeoBench | |
| VPCTnot in indexeffort not stated | – | – | 40.0%#16 | Epoch AI Benchmarking Hub |
Long context
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| AA-LCR | 70.7%#208 | 77.3%#132 | – | Artificial Analysis | |
| Arena Documentnot in indexeffort not stated | – | – | 1465#21 | Arena (LMArena) |
Composite
| Benchmark | no reasoning | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | 150.1#57 | Epoch AI Benchmarking Hub | |
| LiveBench 1.0not in index | – | 72.6%#49 | – | – | LiveBench | |
| AA Intelligence Index v4.3.2 | 23.7#184 | – | 29.1#131 | – | Artificial Analysis | |
| Vals RSI Indexnot in index | – | 14.8%#24 | – | – | Vals AI |
Safety & honesty
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| FORTRESSnot in index | 9.6%#65 | 13.6%#57 | Scale AI SEAL | |
| MASKnot in indexpossible contamination | 92.5%#5 | 87.1%#12 | 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 |
|---|---|---|---|---|---|---|
| Google Vertex | 53 tok/s | 7.08 s | $5.00 | $25.00 | 200k | – |
| Anthropic | 47 tok/s | 0.95 s | $5.00 | $25.00 | 200k | – |
| Claude Platform on AWS | 42 tok/s | 1.20 s | $5.00 | $25.00 | 200k | – |
| Amazon Bedrock | 39 tok/s | 1.54 s | $5.00 | $25.00 | 200k | – |
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 | 23.8 s |
| Summarize a 30-page report | 12,000 / 600 | $0.075 | $0.035 | 28.9 s |
| Code edit | 6,000 / 1,500 | $0.068 | $0.047 | 43.9 s |
| Agentic coding session | 60,000 / 4,000 | $0.400 | $0.198 | 1.4 min |
| Structured extraction | 2,000 / 200 | $0.015 | $0.0083 | 22.2 s |
More from Anthropic
Compare Claude Opus 4.5 with…
- Claude Opus 4.5 vs Claude Opus 5.5
- Claude Opus 4.5 vs Gemini 4 Argon
- Claude Opus 4.5 vs Muse Wonder Full
- Claude Opus 4.5 vs Claude Fable 5.1
- Claude Opus 4.5 vs GPT-6 Astra
- Claude Opus 4.5 vs GPT-6.1 Sol
- Claude Opus 4.5 vs Claude Fable 5
- Claude Opus 4.5 vs Claude Sonnet 5.5
- Claude Opus 4.5 vs Claude Opus 5
- Claude Opus 4.5 vs GPT-5.6 Sol
See also
Questions people ask
- What are Claude Opus 4.5's benchmark scores?
- As of 24 Oct 2026, Claude Opus 4.5 (thinking effort) scores 59.9 ±2.8 on the BenchLeader Index, strongest in agents & tools (75) and weakest in instruction following (54). That rests on 24 independent benchmark results, and every score on this page links to its publisher.
- How does Claude Opus 4.5 rank?
- Claude Opus 4.5 (thinking effort) is #119 of 785 ranked configurations on 24 Oct 2026. 211 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 4.5 cost per 1M tokens?
- As of 24 Oct 2026, Claude Opus 4.5 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 4.5 better than GPT-5.6 Sol?
- As of 24 Oct 2026, GPT-5.6 Sol (max) is the better pick for most workloads: it leads on quality (68.0 vs 59.9 on the BenchLeader Index) and costs 1.3× less. The head-to-head page has the benchmark-by-benchmark detail.
- When was Claude Opus 4.5 released?
- Anthropic released Claude Opus 4.5 on 24 Nov 2025. BenchLeader has results for it at 6 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Claude Opus 4.5: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/claude-opus-4-5.