Multimodal
Like-for-like- Claude Opus 4.6
- 77.3
- dots3-note Preview
- 79.1
- Weighted basis
- 1 vs 1 rows
- Reading
- dots3-note Preview leads
Claude Opus 4.6 vs dots3-note Preview
Updated August 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
7 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Long documents
Prompts that approach the documented context limit
Claude Opus 4.6
Claude Opus 4.6 has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
26 Claude Opus 4.6 only
7 Shared
24 dots3-note Preview only
- Shared results
- 7
- Claude Opus 4.6 only
- 26
- dots3-note Preview only
- 24
- Like-for-like categories
- 1 / 8
3 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Agentic
Directional only- Claude Opus 4.6
- 73.0
- dots3-note Preview
- 83.3
- Weighted basis
- 3 vs 1 rows
- Reading
- Directional only
Coding
Directional only- Claude Opus 4.6
- 68.1
- dots3-note Preview
- 71.7
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Knowledge
Directional only- Claude Opus 4.6
- 69.1
- dots3-note Preview
- 52.6
- Weighted basis
- 4 vs 1 rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 4.6
- Not measured
- dots3-note Preview
- 81.4
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 4.6
- 36.3
- dots3-note Preview
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.6
- Not measured
- dots3-note Preview
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.6
- Not measured
- dots3-note Preview
- 85.1
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
| Category | Claude Opus 4.6 | dots3-note Preview | Weighted basis | Reading |
|---|---|---|---|---|
| Multimodal | 77.3 | 79.1 | Like-for-like1 vs 1 rows | dots3-note Preview leads |
| Agentic | 73.0 | 83.3 | Directional only3 vs 1 rows | Directional only |
| Coding | 68.1 | 71.7 | Directional only3 vs 2 rows | Directional only |
| Knowledge | 69.1 | 52.6 | Directional only4 vs 1 rows | Directional only |
| Reasoning | Not measured | 81.4 | Not comparable0 vs 1 rows | Not comparable |
| Math | 36.3 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | 85.1 | Not comparable0 vs 2 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
SWE-bench Pro
Coding
Claude Opus 4.6: 53.4%dots3-note Preview: 61%Normalized gap 7.6Claude Opus 4.6 source dots3-note Preview sourceSWE-bench Verified
Coding
Claude Opus 4.6: 80.8%dots3-note Preview: 78.4%Normalized gap 2.4Claude Opus 4.6 source dots3-note Preview sourceMMMU-Pro
Multimodal
Claude Opus 4.6: 77.3%dots3-note Preview: 79.1%Normalized gap 1.8Claude Opus 4.6 source dots3-note Preview sourceBrowseComp
Agentic
Claude Opus 4.6: 83.7%dots3-note Preview: 83.3%Normalized gap 0.4Claude Opus 4.6 source dots3-note Preview sourceHLE
Knowledge
Claude Opus 4.6: 53%dots3-note Preview: 52.6%Normalized gap 0.4Claude Opus 4.6 source dots3-note Preview source
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Claude Opus 4.6
- $0.0175
- Fits in one request
- dots3-note Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
dots3-note Preview has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 4.6
- $0.325
- Fits in one request
- dots3-note Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
dots3-note Preview has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Opus 4.6
- $1.35
- Fits in one request
- Cached input priced at the published list-input rate
- dots3-note Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate. dots3-note Preview has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 4.6dots3-note Preview
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.6
1M
dots3-note Preview
API model ID
Claude Opus 4.6
Not sourced
dots3-note Preview
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.6
Not published
dots3-note Preview
No comparable hosted API rate
dots3-note Preview model cardDocumented inputs
Claude Opus 4.6
Not sourced
dots3-note Preview
Not sourced
Documented outputs
Claude Opus 4.6
Not sourced
dots3-note Preview
Not sourced
Provider availability
Claude Opus 4.6
Not sourced
dots3-note Preview
Not sourced
Reasoning profile
Claude Opus 4.6
Non-Reasoning
dots3-note Preview
Reasoning
Weight access
Claude Opus 4.6
Proprietary
dots3-note Preview
Open Weight
License
Claude Opus 4.6
Proprietary
dots3-note Preview
Open Weight
Release date
Claude Opus 4.6
2026-02-01
dots3-note Preview
2026-08-14
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Claude Opus 4.6 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence57 rows
Agentic
Terminal-Bench 2.0
Claude Opus 4.665.4%Sourcedots3-note Preview—Not directly comparable
BrowseComp
Claude Opus 4.683.7%Sourcedots3-note Preview83.3%SourceClaude Opus 4.6 leads this result
OSWorld-Verified
Claude Opus 4.672.7%Sourcedots3-note Preview—Not directly comparable
Claw-Eval
Claude Opus 4.670.4%Sourcedots3-note Preview73.4%Sourcedots3-note Preview leads this result
DeepSearchQA
Claude Opus 4.673.7%Sourcedots3-note Preview92.1%Sourcedots3-note Preview leads this result
CyberGym
Claude Opus 4.666.6%Sourcedots3-note Preview—Not directly comparable
Gert Labs
Claude Opus 4.661.85%Sourcedots3-note Preview—Not directly comparable
ResearchClawBench
Claude Opus 4.619.9%Sourcedots3-note Preview—Not directly comparable
JobBench
Claude Opus 4.636.7%Sourcedots3-note Preview—Not directly comparable
Terminal-Bench 2.1
Claude Opus 4.6—dots3-note Preview75.1%SourceNot directly comparable
Toolathlon-Verified
Claude Opus 4.6—dots3-note Preview55.6%SourceNot directly comparable
skillsBench
Claude Opus 4.6—dots3-note Preview52.8%SourceNot directly comparable
APEX-Agents
Claude Opus 4.6—dots3-note Preview30.8%SourceNot directly comparable
HLE w/ tools
Claude Opus 4.6—dots3-note Preview52.6%SourceNot directly comparable
WideResearch
Claude Opus 4.6—dots3-note Preview78.9%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.680.8%Sourcedots3-note Preview78.4%SourceClaude Opus 4.6 leads this result
SWE-bench Verified*
Claude Opus 4.675.6%Sourcedots3-note Preview—Not directly comparable
LiveCodeBench Pro
Claude Opus 4.670.7%Sourcedots3-note Preview—Not directly comparable
SWE-bench Pro
Claude Opus 4.653.4%Sourcedots3-note Preview61%Sourcedots3-note Preview leads this result
SWE-Rebench
Claude Opus 4.665.3%Sourcedots3-note Preview—Not directly comparable
React Native Evals
Claude Opus 4.684.1%Sourcedots3-note Preview—Not directly comparable
Vibe Code Bench
Claude Opus 4.657.57%Sourcedots3-note Preview—Not directly comparable
FrontierCode 1.1 Main
Claude Opus 4.626.9%Sourcedots3-note Preview—Not directly comparable
Codeforces
Claude Opus 4.6—dots3-note Preview3056.0SourceNot directly comparable
LiveCodeBench v6
Claude Opus 4.6—dots3-note Preview91.5%SourceNot directly comparable
Terminal-Bench 2.1
Claude Opus 4.6—dots3-note Preview75.1%SourceNot directly comparable
SWE Multilingual
Claude Opus 4.6—dots3-note Preview75.7%SourceNot directly comparable
NL2Repo
Claude Opus 4.6—dots3-note Preview49.8%SourceNot directly comparable
Reasoning
ARC-AGI-2
Claude Opus 4.6—dots3-note Preview81.4%SourceNot directly comparable
Knowledge
GPQA
Claude Opus 4.691.3%Sourcedots3-note Preview—Not directly comparable
GPQA-D
Claude Opus 4.689.2%Sourcedots3-note Preview—Not directly comparable
SuperGPQA
Claude Opus 4.695%Sourcedots3-note Preview—Not directly comparable
MMLU-Pro
Claude Opus 4.682%Sourcedots3-note Preview—Not directly comparable
MMLU-Pro (Arcee)
Claude Opus 4.689.1%Sourcedots3-note Preview—Not directly comparable
HLE
Claude Opus 4.653%Sourcedots3-note Preview52.6%SourceClaude Opus 4.6 leads this result
HLE w/o tools
Claude Opus 4.640%Sourcedots3-note Preview—Not directly comparable
HealthBench Hard
Claude Opus 4.614.8%Sourcedots3-note Preview—Not directly comparable
MedXpertQA (Text)
Claude Opus 4.652.1%Sourcedots3-note Preview—Not directly comparable
Math
AIME25 (Arcee)
Claude Opus 4.699.8%Sourcedots3-note Preview—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Opus 4.640.700%Sourcedots3-note Preview—Not directly comparable
FrontierMath v2 (Tier 4)
Claude Opus 4.622.900%Sourcedots3-note Preview—Not directly comparable
IMOAnswerBench
Claude Opus 4.6—dots3-note Preview90.9%SourceNot directly comparable
Multimodal
MMMU-Pro
Claude Opus 4.677.3%Sourcedots3-note Preview79.1%Sourcedots3-note Preview leads this result
ERQA
Claude Opus 4.651.6%Sourcedots3-note Preview—Not directly comparable
ScreenSpot Pro
Claude Opus 4.683.1%Sourcedots3-note Preview—Not directly comparable
MedXpertQA (MM)
Claude Opus 4.664.8%Sourcedots3-note Preview—Not directly comparable
SimpleVQA
Claude Opus 4.6—dots3-note Preview72.5%SourceNot directly comparable
MathVision
Claude Opus 4.6—dots3-note Preview87.7%SourceNot directly comparable
ZeroBench
Claude Opus 4.6—dots3-note Preview19.0%SourceNot directly comparable
CharXiv w/o tools
Claude Opus 4.6—dots3-note Preview83.1%SourceNot directly comparable
GDP.pdf (no tools)
Claude Opus 4.6—dots3-note Preview60.7%SourceNot directly comparable
PerceptionBench
Claude Opus 4.6—dots3-note Preview53.4%SourceNot directly comparable
BabyVision
Claude Opus 4.6—dots3-note Preview50.0%SourceNot directly comparable
MMVU
Claude Opus 4.6—dots3-note Preview79.9%SourceNot directly comparable
VideoMMMU
Claude Opus 4.6—dots3-note Preview86.8%SourceNot directly comparable
Instruction following
Frequently asked questions
Which is better, Claude Opus 4.6 or dots3-note Preview?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Claude Opus 4.6 or dots3-note Preview?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Claude Opus 4.6 or dots3-note Preview?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Opus 4.6 or dots3-note Preview?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Claude Opus 4.6 or dots3-note Preview?
Claude Opus 4.6 has the larger documented context window: 1M, compared with 512K.
Related comparisons
Last updated August 14, 2026
Watch Claude Opus 4.6 vs dots3-note Preview
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.