AnthropicClaude Opus 4.1
Claude Opus 4.1 is an Anthropic proprietary reasoning model, released 5 Aug 2025. Its best configuration (thinking reasoning effort) ranks #204 of 785 on the BenchLeader Index at 56.4 ±2.9, in the upper half. The ± is the point: 250 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 (64) and lowest in reasoning (49). At $30.00 per million tokens blended it is among the most expensive ranked models. Output speed of 13 tokens per second puts it in the slowest quarter, with a first token in 3.9 s. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 22 Oct 2026.
- Blended price
- $30.00/M
- $15.00 in · $75.00 out
- Output speed
- 13 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 3.92 s
- Context
- 200k
- Full answer
- –
- Cost per run
- –
- Released
- 5 Aug 2025
- Overall index56
- Reasoning49
- Coding53
- Agents & tools64
- Maths61
- Knowledge58
- Instruction following51
- Human preference64
- Multimodal56
- Long context63
- Composite55
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 4.5thinking | 24 Nov 2025 | 59.9 | #119 |
| Claude Opus 4.1thinkingthis page | 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 | – | – | 13 tok/s | 3.92 s | $0.029 | Composite 50 |
| thinkingbest | 56.4 | #204 | 13 tok/s | 3.92 s | $0.029 | Agents & tools 64 · Coding 53 · Composite 55 · Human preference 64 · Instruction following 51 · Knowledge 58 · Long context 63 · Maths 61 · Multimodal 56 · Reasoning 49 |
| not stated | 51.5 | #341 | 13 tok/s | 3.92 s | $0.029 | Agents & tools 53 · Coding 49 · Human preference 63 · Instruction following 40 · Knowledge 49 · Maths 47 · Multimodal 59 · Reasoning 54 |
How its index has moved
8 Sept 2026 to 21 Oct 2026- thinking
- 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 | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| GPQA Diamondeffort not stated | – | 77.3%#136 | Epoch AI Benchmarking Hub | |
| Humanity's Last Exameffort not stated | – | 11.5%#29 | Scale AI / CAIS | |
| SimpleBencheffort not stated | – | 60.0%#31 | SimpleBench | |
| Arena Hard Prompts | 1480#66 | 1478#68 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 80.9%#188 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 12.5%#279 | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 76.3%#75 | 70.0%#90 | Vals AI | |
| CritPt | 0.0%#315 | – | Artificial Analysis | |
| SciPredictnot in indexeffort not stated | – | 22.2%#4 | Scale AI SEAL | |
| Mystery Game Puzzlesnot in indexeffort not stated | – | 21.0%#58 | Epoch AI Benchmarking Hub | |
| LMCAnot in indexeffort not stated | – | 37.1%#120 | Epoch AI Benchmarking Hub | |
| DTBenchnot in indexeffort not stated | – | 80.0%#132 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in indexeffort not stated | – | 64.7%#21 | ForecastBench |
Coding
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| SWE-bench Verified (Epoch)effort not stated | – | 73.3%#20 | Epoch AI Benchmarking Hub | |
| WeirdMLeffort not stated | – | 45.9%#82 | WeirdML | |
| Arena Coding | 1511#56 | 1505#69 | Arena (LMArena) | |
| Arena WebDeveffort not stated | – | 1390#96 | Arena (LMArena) | |
| LiveCodeBench | 66.5%#94 | 64.6%#96 | Vals AI | |
| ALE-Benchnot in indexeffort not stated | – | 674.8#88 | Epoch AI Benchmarking Hub | |
| AlgoTunenot in indexeffort not stated | – | 1.3#16 | AlgoTune |
Agents & tools
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| Terminal-Bencheffort not stated | – | 38.0%#48 | Terminal-Bench | |
| GDPvaleffort not stated | – | 43.6%#3 | OpenAI | |
| Cybencheffort not stated | – | 42.0%#5 | Cybench | |
| Terminal-Bench Hard | 34.3%#88 | – | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 71.4%#152 | – | Artificial Analysis | |
| DeepResearch Benchnot in indexeffort not stated | – | 48.3%#19 | DeepResearch Bench | |
| METR Time Horizonsnot in indexeffort not stated | – | 66.8%#13 | METR | |
| BrowseCompnot in indexeffort not stated | – | 1.0%#16 | OpenAI |
Maths
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3effort not stated | – | 12.6%#103 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4effort not stated | – | 2.4%#68 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIMEeffort not stated | – | 68.9%#141 | Epoch AI Benchmarking Hub | |
| AIME (Vals) | 78.2%#48 | 44.2%#62 | Vals AI | |
| MGSM | 94.4%#3 | 94.2%#5 | Vals AI | |
| MATH 500not in index | 95.4%#4 | 93.0%#17 | Vals AI | |
| Arena Maths | 1444#86 | 1433#102 | Arena (LMArena) |
Knowledge
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| MMLU-Pro | 87.9%#23 | 87.2%#33 | Vals AI | |
| LegalBencheffort not stated | – | 83.5%#53 | Vals AI | |
| TaxEval | 73.7%#46 | 71.5%#75 | Vals AI | |
| MedQA | 93.6%#22 | 92.5%#29 | Vals AI | |
| PRBench Financeeffort not stated | – | 35.1%#33 | Scale AI SEAL | |
| PRBench Legaleffort not stated | – | 34.0%#40 | Scale AI SEAL | |
| MultiNRCpossible contamination | 38.4%#19 | 29.7%#23 | Scale AI SEAL | |
| MedCodenot in index | 47.2%#35 | 41.4%#53 | Vals AI | |
| MedScribenot in index | 73.9%#80 | 71.8%#88 | Vals AI | |
| EBR-benchnot in indexeffort not stated | – | 7.9%#24 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| IFBench | 55.4%#146 | – | Artificial Analysis | |
| MultiChallenge | 57.2%#18 | – | Scale AI SEAL | |
| TutorBench | 50.8%#17 | 47.4%#22 | Scale AI SEAL | |
| Arena Instruction Followingnot in index | 1458#53 | 1454#58 | Arena (LMArena) |
Human preference
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Text | 1450#77 | 1448#79 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1446#48 | 1442#56 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1471#59 | 1469#63 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1485#38 | 1472#59 | Arena (LMArena) | |
| Lech Mazur Creative Writingnot in indexeffort not stated | – | 84.7%#3 | Lech Mazur |
Multimodal
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| MMMU-Pro | 67.9%#165 | – | Artificial Analysis | |
| VISTA | 48.4%#15 | 45.3%#28 | Scale AI SEAL | |
| MMMU (validation)effort not stated | – | 77.1%#12 | MMMU | |
| MMMU-Pro (Vals)not in index | 77.5%#50 | 73.7%#56 | Vals AI | |
| MortgageTaxnot in index | 56.1%#73 | 61.1%#61 | Vals AI | |
| SAGEnot in index | 30.4%#79 | 31.4%#75 | Vals AI | |
| VTBnot in index | 5.2%#14 | 4.7%#15 | Scale AI SEAL | |
| VPCTnot in indexeffort not stated | – | 35.0%#26 | Epoch AI Benchmarking Hub |
Long context
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| AA-LCR | 76.0%#148 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | 144.1#90 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 18.6#251 | 22.9#195 | – | Artificial Analysis |
Safety & honesty
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| FORTRESSnot in index | 14.8%#55 | 16.1%#51 | Scale AI SEAL | |
| MASKnot in indexpossible contamination | 94.2%#4 | 87.4%#11 | 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 |
|---|---|---|---|---|---|---|
| Amazon Bedrock | 13 tok/s | 3.98 s | $15.00 | $75.00 | 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 $1.50 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.029 | $0.025 | 27.0 s |
| Summarize a 30-page report | 12,000 / 600 | $0.225 | $0.103 | 50.1 s |
| Code edit | 6,000 / 1,500 | $0.203 | $0.142 | 2.0 min |
| Agentic coding session | 60,000 / 4,000 | $1.20 | $0.593 | 5.2 min |
| Structured extraction | 2,000 / 200 | $0.045 | $0.025 | 19.3 s |
More from Anthropic
See also
Questions people ask
- What are Claude Opus 4.1's benchmark scores?
- As of 24 Oct 2026, Claude Opus 4.1 (thinking effort) scores 56.4 ±2.9 on the BenchLeader Index, strongest in agents & tools (64) and weakest in reasoning (49). That rests on 20 independent benchmark results, and every score on this page links to its publisher.
- How does Claude Opus 4.1 rank?
- Claude Opus 4.1 (thinking effort) is #204 of 785 ranked configurations on 24 Oct 2026. 250 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 4.1 cost per 1M tokens?
- As of 24 Oct 2026, Claude Opus 4.1 costs $15.00 per 1M input tokens and $75.00 per 1M output tokens, $30.00 blended (three input tokens per output token).
- When was Claude Opus 4.1 released?
- Anthropic released Claude Opus 4.1 on 5 Aug 2025. BenchLeader has results for it at 3 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Claude Opus 4.1: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/claude-opus-4-1.