Data as of October 17, 2026 · How the score is built
Released February 20261M context
Claude Opus 4.6
Decision readingClaude Opus 4.6 scores 62.4 out of 100 and ranks #47 of 224. This profile shows 36 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #25. API pricing is $5 input and $25 output per million tokens.
Released February 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
62.4/100
field median 49.6#47 of 224 ranked models
Public
#47of 224
Verified #31 of 88
Price
$5input / $25 output
input median $0.75blended $15
Speed
43tok/s
field median 92 tok/sFirst token 2.24 s
Context
1Mtokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Multimodal & Grounded ranks #25. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
36 published rows leave some tracked benchmark slots empty. Agentic is its lowest eligible category at #57.
Source-linked · 36 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #57 of 128Percentile 56thWeight 22%11 benchmarksMixed sources | 45.7 | 11 benchmarks | Mixed sources | |||
| CodingRank #52 of 150Percentile 66thWeight 20%9 benchmarksMixed sources | 46.1 | 9 benchmarks | Mixed sources | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalRank #25 of 54Percentile 55thWeight 12%4 benchmarksMixed sources | 74.5 | 4 benchmarks | Mixed sources | |||
| KnowledgeRank #52 of 184Percentile 72ndWeight 12%9 benchmarksMixed sources | 59.0 | 9 benchmarks | Mixed sources | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathRank Not rankedWeight 5%3 benchmarksMixed sources | 69.1 | 3 benchmarks | Mixed sources |
36 of 681 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic9/11 verified
- Coding6/9 verified
- ReasoningNot measured
- Multimodal1/4 verified
- Knowledge2/9 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math2/3 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Claude Opus 4.6 category percentile values
- Agentic56th percentile
- Coding66th percentile
- ReasoningNot eligible
- Multimodal55th percentile
- Knowledge72nd percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#57/128
- Coding#52/150
- ReasoningNot ranked
- Multimodal#25/54
- Knowledge#52/184
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding9 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score53.4% | Versus best verified row Best verified: Claude Opus 5.5 · 89.9% | Gap36.5 behind | Weight26% ref. weight | Secondary exact |
| SWE-Rebench | Score65.3% | Versus best verified row Best verified: Claude Opus 4.6 · 65.3% | GapBest verified | Weight5% ref. weight | Benchmark exact |
| FrontierCode 1.1 Main | Score26.9% | Versus best verified row Best verified: Claude Opus 5.5 · 54.4% | Gap27.5 behind | Weight4% ref. weight | Benchmark exact |
| Terminal-Bench 2.0 | Score65.4% | Versus best verified row Best verified: GPT-5.5 · 82.0% | Gap16.6 behind | WeightScored in Agentic | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score80.8% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap15.2 behind | WeightDisplay only | Provider exact |
| SWE-bench Verified*SWE-bench Verified (mini-swe-agent-v2) | Score75.6% | Versus best verified row | GapNo verified comparator | WeightDisplay only | Secondary exact |
| LiveCodeBench Pro | Score70.7% | Versus best verified row Best verified: Sakana Fugu-Ultra · 90.8% | Gap20.1 behind | WeightDisplay only | Secondary exact |
| React Native Evals | Score84.1% | Versus best verified row Best verified: Composer 2 · 96.1% | Gap12 behind | WeightDisplay only | Benchmark exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score57.57% | Versus best verified row Best verified: Gemini 4 Argon · 91.90% | Gap34.3 behind | WeightDisplay only | Benchmark exact |
Agentic11 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BrowseComp | Score83.7% | Versus best verified row Best verified: Atria Dawn Preview · 92.5% | Gap8.8 behind | Weight8% ref. weight | Provider exact |
| Terminal-Bench 2.0 | Score65.4% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap16.6 behind | Weight7% ref. weight | Provider exact |
| OSWorld-Verified | Score74% | Versus best verified row Best verified: Qwen3.8 Max · 86.1% | Gap12.1 behind | Weight7% ref. weight | Provider exact |
| JobBench | Score36.7% | Versus best verified row Best verified: Muse Wonder Full · 75.3% | Gap38.6 behind | Weight6% ref. weight | Benchmark exact |
| DeepSearchQA | Score73.7% | Versus best verified row Best verified: Atria Dawn Preview · 96.0% | Gap22.3 behind | Weight2% ref. weight | Secondary exact |
| AndroidWorld | Score62.0% | Versus best verified row Best verified: Qwen3.8-Omni-Flash · 87.1% | Gap25.1 behind | WeightDisplay only | Secondary exact |
| Claw-Eval | Score70.4% | Versus best verified row Best verified: Ornith-1.5-397B · 81.4% | Gap11 behind | WeightDisplay only | Benchmark exact |
| CyberGym | Score66.6% | Versus best verified row Best verified: MiMo-V2.6-Flash · 95.1% | Gap28.5 behind | WeightDisplay only | Benchmark exact |
| Gert LabsGert Labs Composite Game Benchmark | Score61.85% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap11.1 behind | WeightDisplay only | Benchmark exact |
| ResearchClawBench | Score19.9% | Versus best verified row Best verified: Claude Opus 4.8 · 21.1% | Gap1.2 behind | WeightDisplay only | Benchmark exact |
| ApprenticeBenchApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job | Score5% | Versus best verified row Best verified: Claude Fable 5.1 · 72% | Gap67 behind | WeightDisplay only | Benchmark exact |
Multimodal4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | Score77.3% | Versus best verified row Best verified: Gemini 3.5 Flash · 83.6% | Gap6.3 behind | WeightWeighted 40% | Provider exact |
| ERQA | Score51.6% | Versus best verified row Best verified: Qwen3.8 Max · 77.8% | Gap26.2 behind | WeightDisplay only | Secondary exact |
| ScreenSpot Pro | Score83.1% | Versus best verified row Best verified: GPT-6 Astra · 92.7% | Gap9.6 behind | WeightDisplay only | Secondary exact |
| MedXpertQA (MM)MedXpertQA Multimodal | Score64.8% | Versus best verified row Best verified: Qwen3.8 Max · 80.4% | Gap15.6 behind | WeightDisplay only | Secondary exact |
Knowledge9 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score53% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap12 behind | Weight44% ref. weight | Provider exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score40% | Versus best verified row Best verified: Claude Opus 5.5 · 64.4% | Gap24.4 behind | Weight7% ref. weight | Secondary exact |
| MMLU-ProMassive Multitask Language Understanding Professional | Score82% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap7.6 behind | Weight6% ref. weight | Secondary exact |
| GPQAGraduate-Level Google-Proof Q&A | Score91.3% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap4.7 behind | Weight3% ref. weight | Provider exact |
| SuperGPQASuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | Score95% | Versus best verified row Best verified: Qwen 3.6 Max (preview) · 73.9% | Gap21.1 behind | Weight2% ref. weight | Secondary exact |
| GPQA-DGPQA Diamond | Score89.2% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap6.8 behind | WeightDisplay only | Secondary exact |
| MMLU-Pro (Arcee)MMLU-Pro first-party comparison snapshot | Score89.1% | Versus best verified row Best verified: Trinity-Large-Preview · 75.2% | Gap13.9 behind | WeightDisplay only | Secondary exact |
| HealthBench Hard | Score14.8% | Versus best verified row Best verified: Muse Spark · 42.8% | Gap28 behind | WeightDisplay only | Secondary exact |
| MedXpertQA (Text)MedXpertQA Text | Score52.1% | Versus best verified row Best verified: Muse Spark · 52.6% | Gap0.5 behind | WeightDisplay only | Secondary exact |
Math3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | Score65.965% | Versus best verified row Best verified: GPT-6 Astra · 93.684% | Gap27.7 behind | WeightWeighted 30% | Benchmark exact |
| FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4 | Score26.829% | Versus best verified row Best verified: GPT-6.1 Sol · 100.000% | Gap73.2 behind | WeightWeighted 10% | Benchmark exact |
| AIME25 (Arcee)AIME25 first-party comparison snapshot | Score99.8% | Versus best verified row Best verified: Trinity-Large-Preview · 24.0% | Gap75.8 behind | WeightDisplay only | Secondary exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 36 rowsWhat it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
Claude Opus 4.6 · 62.4 score · $15 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Published price history
This chart appears only when at least two dated first-party price records exist for the exact model. It shows rate changes, not an inferred cost trend.
3 dated first-party price records. The newest record lists $25 per million tokens.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Claude Opus 4.6 (Adaptive)Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 1M
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Superseded
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Claude Opus 4.6 ranks #47 of 224 on the public leaderboard with a score of 62.39/100. Its source-verified position is #31 of 88.
Claude Opus 4.6 is a proprietary model with a 1M context window. No explicit reasoning mode is documented in this profile.
Claude Opus 4.6 sits in the Claude Opus 4.6 family with Claude Opus 4.6 (Adaptive). 36 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #25, while its lowest eligible position is Agentic at #57. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Last updated October 17, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Claude Opus 4.6 perform overall in AI benchmarks?
Claude Opus 4.6 ranks #47 out of 224 models on the public BenchAlign leaderboard, with a score of 62.39/100. Its evidence status is Supported, and this profile shows 36 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Claude Opus 4.6 good for knowledge and understanding?
Claude Opus 4.6 ranks #52 out of 184 eligible models for knowledge and understanding, with a public category score of 59/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Claude Opus 4.6 good for coding and programming?
Claude Opus 4.6 ranks #52 out of 150 eligible models for coding and programming, with a public category score of 46.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Claude Opus 4.6 good for mathematics?
Claude Opus 4.6 has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Claude Opus 4.6 good for agentic tool use and computer tasks?
Claude Opus 4.6 ranks #57 out of 128 eligible models for agentic tool use and computer tasks, with a public category score of 45.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Claude Opus 4.6 good for multimodal and grounded tasks?
Claude Opus 4.6 ranks #25 out of 54 eligible models for multimodal and grounded tasks, with a public category score of 74.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Which sibling models are related to Claude Opus 4.6?
Claude Opus 4.6 belongs to the Claude Opus 4.6 family. Related tracked variants include Claude Opus 4.6 (Adaptive). A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Claude Opus 4.6 have full benchmark coverage on BenchLM?
No. Claude Opus 4.6 currently has 48 source-displayable rows across 681 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Claude Opus 4.6?
Claude Opus 4.6 has a reported context window of 1M in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.