Data as of October 20, 2026 · How the score is built
Released Apr 16, 20261M context
Claude Opus 4.7 (Adaptive)
Decision readingClaude Opus 4.7 (Adaptive) scores 68.7 out of 100 and ranks #23 of 227. This profile shows 21 source-displayable benchmark rows; its strongest eligible category is Agentic at #29. API pricing is $5 input and $25 output per million tokens.
Released Apr 16, 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
68.7/100
field median 49.8#23 of 227 ranked models
Public
#23of 227
Verified —
Price
$5input / $25 output
input median $0.72blended $15
Speed
Not measured
field median 93.5 tok/sTime to first token not measured
Context
1Mtokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Agentic ranks #29. Particularly useful for coding agents, browser research, and computer-use workflows.
Validate before choosing
21 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Source-linked · 21 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 #29 of 131Percentile 78thWeight 22%7 benchmarksMixed sources | 59.7 | 7 benchmarks | Mixed sources | |||
| CodingRank #32 of 152Percentile 79thWeight 20%3 benchmarksVerified | 55.5 | 3 benchmarks | Verified | |||
| ReasoningRank Not rankedWeight 17%3 benchmarksMixed sources | 57.4 | 3 benchmarks | Mixed sources | |||
| MultimodalRank #47 of 55Percentile 15thWeight 12%3 benchmarksMixed sources | 53.7 | 3 benchmarks | Mixed sources | |||
| KnowledgeRank #30 of 187Percentile 84thWeight 12%4 benchmarksVerified | 66.2 | 4 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%1 benchmarkReported | Score pending | 1 benchmark | Reported |
21 of 726 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.
- Agentic6/7 verified
- Coding3/3 verified
- Reasoning1/3 verified
- Multimodal2/3 verified
- Knowledge4/4 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math0/1 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 4.7 (Adaptive) category percentile values
- Agentic78th percentile
- Coding79th percentile
- ReasoningNot eligible
- Multimodal15th percentile
- Knowledge84th percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#29/131
- Coding#32/152
- ReasoningNot ranked
- Multimodal#47/55
- Knowledge#30/187
- 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.
Coding3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score64.3% | Versus best verified row Best verified: Claude Opus 5.5 · 89.9% | Gap25.6 behind | Weight26% ref. weight | Provider exact |
| Terminal-Bench 2.0 | Score69.4% | Versus best verified row Best verified: GPT-5.5 · 82.0% | Gap12.6 behind | WeightScored in Agentic | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score87.6% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap8.4 behind | WeightDisplay only | Provider exact |
Agentic7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BrowseComp | Score79.3% | Versus best verified row Best verified: Atria Dawn Preview · 92.5% | Gap13.2 behind | Weight8% ref. weight | Provider exact |
| Terminal-Bench 2.0 | Score69.4% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap12.6 behind | Weight7% ref. weight | Provider exact |
| OSWorld-Verified | Score78% | Versus best verified row Best verified: Qwen3.8 Max · 86.1% | Gap8.1 behind | Weight7% ref. weight | Provider exact |
| JobBench | Score45.9% | Versus best verified row Best verified: Muse Wonder Full · 75.3% | Gap29.4 behind | Weight6% ref. weight | Benchmark exact |
| MCP Atlas | Score77.3% | Versus best verified row Best verified: Muse Spark Open · 89.2% | Gap11.9 behind | Weight4% ref. weight | Provider exact |
| CyberGym | Score73.1% | Versus best verified row Best verified: MiMo-V2.6-Flash · 95.1% | Gap22 behind | WeightDisplay only | Secondary exact |
| OSWorld 2.0 | Score18.2% | Versus best verified row Best verified: GPT-6 Astra · 72.6% | Gap54.4 behind | WeightDisplay only | Benchmark exact |
Reasoning3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | Score75.8% | Versus best verified row Best verified: GPT-6 Astra · 95% | Gap19.2 behind | WeightWeighted 25% | Secondary exact |
| ARC-AGI-3Abstraction and Reasoning Corpus for AGI v3 | Score0.2% | Versus best verified row Best verified: GPT-6 Astra · 62.7% | Gap62.5 behind | WeightWeighted 15% | Benchmark exact |
| MRCR v2 128K-256KOpenAI MRCR v2 8-needle 128K-256K | Score59.2% | Versus best verified row Best verified: GPT-5.5 · 87.5% | Gap28.3 behind | WeightDisplay only | Secondary exact |
Multimodal3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| OfficeQA Pro | Score43.6% | Versus best verified row Best verified: Claude Opus 5.5 · 67.7% | Gap24.1 behind | WeightWeighted 25% | Secondary exact |
| CharXivCharXiv Reasoning | Score91% | Versus best verified row Best verified: Qwen3.8 Max · 93.5% | Gap2.5 behind | WeightWeighted 20% | Provider exact |
| CharXiv w/o toolsCharXiv Reasoning without tools | Score82.1% | Versus best verified row Best verified: Claude Mythos 5 · 88.9% | Gap6.8 behind | WeightDisplay only | Provider exact |
Knowledge4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score54.7% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap10.3 behind | Weight44% ref. weight | Provider exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score46.9% | Versus best verified row Best verified: Claude Opus 5.5 · 64.4% | Gap17.5 behind | Weight7% ref. weight | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score94.2% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap1.8 behind | Weight3% ref. weight | Provider exact |
| GPQA-DGPQA Diamond | Score94.2% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap1.8 behind | WeightDisplay only | Provider exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath (legacy)FrontierMath legacy aggregate | Score43.8% | Versus best verified row Best verified: GPT-5.6 Sol · 89% | Gap45.2 behind | WeightDisplay only | Secondary exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 21 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 4.7 (Adaptive) · 68.7 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
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.
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 4.7 (Adaptive) ranks #23 of 227 on the public leaderboard with a score of 68.67/100. It does not yet have enough sourced coverage for a verified position.
Claude Opus 4.7 (Adaptive) is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Claude Opus 4.7 (Adaptive) sits in the Claude Opus 4.7 family with Claude Opus 4.7. Its explicit predecessor is Claude Opus 4.6. 21 of 726 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Agentic at #29, while its lowest eligible position is Multimodal & Grounded at #47. particularly useful for coding agents, browser research, and computer-use workflows.
Last updated October 20, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Claude Opus 4.7 (Adaptive) perform overall in AI benchmarks?
Claude Opus 4.7 (Adaptive) ranks #23 out of 227 models on the public BenchAlign leaderboard, with a score of 68.67/100. Its evidence status is Estimated, and this profile shows 21 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Claude Opus 4.7 (Adaptive) good for knowledge and understanding?
Claude Opus 4.7 (Adaptive) ranks #30 out of 187 eligible models for knowledge and understanding, with a public category score of 66.2/100. 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 4.7 (Adaptive) good for coding and programming?
Claude Opus 4.7 (Adaptive) ranks #32 out of 152 eligible models for coding and programming, with a public category score of 55.5/100. 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.
Is Claude Opus 4.7 (Adaptive) good for mathematics?
Claude Opus 4.7 (Adaptive) 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 4.7 (Adaptive) good for reasoning and logic?
Claude Opus 4.7 (Adaptive) has source-displayable benchmark coverage for reasoning and logic, 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 4.7 (Adaptive) good for agentic tool use and computer tasks?
Claude Opus 4.7 (Adaptive) ranks #29 out of 131 eligible models for agentic tool use and computer tasks, with a public category score of 59.7/100. 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 4.7 (Adaptive) good for multimodal and grounded tasks?
Claude Opus 4.7 (Adaptive) ranks #47 out of 55 eligible models for multimodal and grounded tasks, with a public category score of 53.7/100. 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.
Which sibling models are related to Claude Opus 4.7 (Adaptive)?
Claude Opus 4.7 (Adaptive) belongs to the Claude Opus 4.7 family. Related tracked variants include Claude Opus 4.7. 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 4.7 (Adaptive) have full benchmark coverage on BenchLM?
No. Claude Opus 4.7 (Adaptive) currently has 37 source-displayable rows. 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 4.7 (Adaptive)?
Claude Opus 4.7 (Adaptive) 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.