Data as of October 17, 2026 · How the score is built
Released February 2026200K context
Claude Sonnet 4.6
Decision readingClaude Sonnet 4.6 scores 55.9 out of 100 and ranks #64 of 224. This profile shows 28 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #45. API pricing is $3 input and $15 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
55.9/100
field median 49.6#64 of 224 ranked models
Public
#64of 224
Verified #42 of 88
Price
$3input / $15 output
input median $0.75blended $9
Speed
47tok/s
field median 92 tok/sFirst token 1.15 s
Context
200Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Multimodal & Grounded ranks #45. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
28 published rows leave some tracked benchmark slots empty. Knowledge is its lowest eligible category at #58.
Source-linked · 28 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 #55 of 128Percentile 57thWeight 22%10 benchmarksVerified | 46.3 | 10 benchmarks | Verified | |||
| CodingRank #54 of 150Percentile 64thWeight 20%9 benchmarksVerified | 44.7 | 9 benchmarks | Verified | |||
| ReasoningRank Not rankedWeight 17%2 benchmarksVerified | 62.8 | 2 benchmarks | Verified | |||
| MultimodalRank #45 of 54Percentile 17thWeight 12%1 benchmarkVerified | 58.7 | 1 benchmark | Verified | |||
| KnowledgeRank #58 of 184Percentile 69thWeight 12%6 benchmarksMixed sources | 55.4 | 6 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 | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
28 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.
- Agentic10/10 verified
- Coding9/9 verified
- Reasoning2/2 verified
- Multimodal1/1 verified
- Knowledge4/6 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
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 Sonnet 4.6 category percentile values
- Agentic57th percentile
- Coding64th percentile
- ReasoningNot eligible
- Multimodal17th percentile
- Knowledge69th percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#55/128
- Coding#54/150
- ReasoningNot ranked
- Multimodal#45/54
- Knowledge#58/184
- 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 |
|---|---|---|---|---|---|
| LiveCodeBench (Vals)LiveCodeBench, Vals AI run | Score82.1% | Versus best verified row Best verified: Claude Fable 5.1 · 90.5% | Gap8.4 behind | Weight8% ref. weight | |
| SWE-Rebench | Score60.7% | Versus best verified row Best verified: Claude Opus 4.6 · 65.3% | Gap4.6 behind | Weight5% ref. weight | Benchmark exact |
| FrontierCode 1.1 Main | Score24.3% | Versus best verified row Best verified: Claude Opus 5.5 · 54.4% | Gap30.1 behind | Weight4% ref. weight | Benchmark exact |
| Terminal-Bench 2.0 | Score59.1% | Versus best verified row Best verified: GPT-5.5 · 82.0% | Gap22.9 behind | WeightScored in Agentic | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score79.6% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap16.4 behind | WeightDisplay only | Provider exact |
| React Native Evals | Score80.6% | Versus best verified row Best verified: Composer 2 · 96.1% | Gap15.5 behind | WeightDisplay only | Benchmark exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score51.48% | Versus best verified row Best verified: Gemini 4 Argon · 91.90% | Gap40.4 behind | WeightDisplay only | Benchmark exact |
| cursorBench31 | Score48.8% | Versus best verified row Best verified: Claude Fable 5 · 70.6% | Gap21.8 behind | WeightDisplay only | Benchmark exact |
| SWE-bench (Vals)SWE-bench, Vals AI run | Score77.4% | Versus best verified row Best verified: Claude Opus 5 · 97.0% | Gap19.6 behind | WeightDisplay only | Verified |
Agentic10 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score59.1% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap22.9 behind | Weight7% ref. weight | Provider exact |
| OSWorld-Verified | Score72.1% | Versus best verified row Best verified: Qwen3.8 Max · 86.1% | Gap14 behind | Weight7% ref. weight | Benchmark exact |
| JobBench | Score36.9% | Versus best verified row Best verified: Muse Wonder Full · 75.3% | Gap38.4 behind | Weight6% ref. weight | Benchmark exact |
| Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI run | Score57.3% | Versus best verified row Best verified: GPT-6 Astra · 87.3% | Gap30 behind | Weight4% ref. weight | |
| Claw-Eval | Score67.8% | Versus best verified row Best verified: Ornith-1.5-397B · 81.4% | Gap13.6 behind | WeightDisplay only | Benchmark exact |
| CyberGym | Score65.2% | Versus best verified row Best verified: MiMo-V2.6-Flash · 95.1% | Gap29.9 behind | WeightDisplay only | Benchmark exact |
| Gert LabsGert Labs Composite Game Benchmark | Score62.92% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap10 behind | WeightDisplay only | Benchmark exact |
| OSWorld 2.0 | Score8.3% | Versus best verified row Best verified: GPT-6 Astra · 72.6% | Gap64.3 behind | WeightDisplay only | Benchmark exact |
| ApprenticeBenchApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job | Score2% | Versus best verified row Best verified: Claude Fable 5.1 · 72% | Gap70 behind | WeightDisplay only | Benchmark exact |
| MazeBenchMazeBench: visual spatial reasoning in a 3D open world | Score0% | Versus best verified row Best verified: GPT-6 Astra · 23% | Gap23 behind | WeightDisplay only | Benchmark exact |
Reasoning2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | Score58.3% | Versus best verified row Best verified: GPT-6 Astra · 95% | Gap36.7 behind | WeightWeighted 25% | Benchmark exact |
| ARC-AGI-1ARC-AGI-1 Semi-Private Evaluation | Score86.00% | Versus best verified row Best verified: GPT-6 Astra · 98.50% | Gap12.5 behind | WeightDisplay only | Benchmark exact |
Multimodal1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| CharXivCharXiv Reasoning | Score77.4% | Versus best verified row Best verified: Qwen3.8 Max · 93.5% | Gap16.1 behind | WeightWeighted 20% | Provider exact |
Knowledge6 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score49% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap16 behind | Weight44% ref. weight | Provider exact |
| MMLU-ProMassive Multitask Language Understanding Professional | Score79.2% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap10.4 behind | Weight6% ref. weight | Secondary exact |
| MMLU-Pro (Vals)MMLU-Pro, Vals AI run | Score87.3% | Versus best verified row Best verified: Claude Fable 5.1 · 92.4% | Gap5.1 behind | Weight6% ref. weight | Verified |
| GPQAGraduate-Level Google-Proof Q&A | Score89.9% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap6.1 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 Diamond (Vals)GPQA Diamond, Vals AI run | Score85.6% | Versus best verified row Best verified: Gemini 3.1 Pro · 95.5% | Gap9.9 behind | Weight2% ref. weight |
Bars run 0–100; the dark tick marks the best source-verified value
All 28 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 Sonnet 4.6 · 55.9 score · $9 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.
2 dated first-party price records. The newest record lists $15 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
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
- 200K
- 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 Sonnet 4.6 ranks #64 of 224 on the public leaderboard with a score of 55.89/100. Its source-verified position is #42 of 88.
Claude Sonnet 4.6 is a proprietary model with a 200K context window. No explicit reasoning mode is documented in this profile.
28 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #45, while its lowest eligible position is Knowledge at #58. 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 Sonnet 4.6 perform overall in AI benchmarks?
Claude Sonnet 4.6 ranks #64 out of 224 models on the public BenchAlign leaderboard, with a score of 55.89/100. Its evidence status is Supported, and this profile shows 28 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Claude Sonnet 4.6 good for knowledge and understanding?
Claude Sonnet 4.6 ranks #58 out of 184 eligible models for knowledge and understanding, with a public category score of 55.4/100. 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 Sonnet 4.6 good for coding and programming?
Claude Sonnet 4.6 ranks #54 out of 150 eligible models for coding and programming, with a public category score of 44.7/100. 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 Sonnet 4.6 good for reasoning and logic?
Claude Sonnet 4.6 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 Sonnet 4.6 good for agentic tool use and computer tasks?
Claude Sonnet 4.6 ranks #55 out of 128 eligible models for agentic tool use and computer tasks, with a public category score of 46.3/100. 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 Sonnet 4.6 good for multimodal and grounded tasks?
Claude Sonnet 4.6 ranks #45 out of 54 eligible models for multimodal and grounded tasks, with a public category score of 58.7/100. 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.
Does Claude Sonnet 4.6 have full benchmark coverage on BenchLM?
No. Claude Sonnet 4.6 currently has 40 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 Sonnet 4.6?
Claude Sonnet 4.6 has a reported context window of 200K 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.