Math
Like-for-like- Claude Opus 4.6
- 36.3
- Claude Opus 4.7
- 38.6
- Weighted basis
- 2 vs 2 rows
- Reading
- Claude Opus 4.7 leads
Claude Opus 4.6 vs Claude Opus 4.7
Updated August 29, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Opus 4.7 has the higher public score estimate, 72.33 versus 68.26, but the 90% score intervals overlap. Treat that as a lead, not a settled 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.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
No clear pick
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
No clear pick
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
No clear pick
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
1 Claude Opus 4.7 only
- Shared results
- 7
- Claude Opus 4.6 only
- 26
- Claude Opus 4.7 only
- 1
- Like-for-like categories
- 1 / 8
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
Not comparable- Claude Opus 4.6
- 73.0
- Claude Opus 4.7
- Not measured
- Weighted basis
- 3 vs 0 rows
- Reading
- Not comparable
Coding
Not comparable- Claude Opus 4.6
- 68.1
- Claude Opus 4.7
- Not measured
- Weighted basis
- 3 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Opus 4.6
- Not measured
- Claude Opus 4.7
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Opus 4.6
- 69.1
- Claude Opus 4.7
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.6
- Not measured
- Claude Opus 4.7
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 4.6
- 77.3
- Claude Opus 4.7
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.6
- Not measured
- Claude Opus 4.7
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Opus 4.6 | Claude Opus 4.7 | Weighted basis | Reading |
|---|---|---|---|---|
| Math | 36.3 | 38.6 | Like-for-like2 vs 2 rows | Claude Opus 4.7 leads |
| Agentic | 73.0 | Not measured | Not comparable3 vs 0 rows | Not comparable |
| Coding | 68.1 | Not measured | Not comparable3 vs 0 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | 69.1 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 77.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 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.
FrontierMath v2 (Tiers 1-3)
Math
FrontierMath v2 (Tier 4)
Math
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
- Claude Opus 4.7
- $0.0175
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 4.6
- $0.325
- Fits in one request
- Claude Opus 4.7
- $0.325
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
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
- Claude Opus 4.7
- $1.35
- Fits in one request
- Cached input priced at the published list-input rate
Modeled costs are equal
Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate. Claude Opus 4.7 has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 4.6Claude Opus 4.7
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.6
1M
Claude Opus 4.7
API model ID
Claude Opus 4.6
Not sourced
Claude Opus 4.7
claude-opus-4-7
Anthropic model ID documentationCached-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
Claude Opus 4.7
Not published
Documented inputs
Claude Opus 4.6
Not sourced
Claude Opus 4.7
text, image
Anthropic model overviewDocumented outputs
Claude Opus 4.6
Not sourced
Claude Opus 4.7
Provider availability
Claude Opus 4.6
Not sourced
Claude Opus 4.7
Generally Available · Claude API
Anthropic model overviewReasoning profile
Claude Opus 4.6
Non-Reasoning
Claude Opus 4.7
Non-Reasoning
Weight access
Claude Opus 4.6
Proprietary
Claude Opus 4.7
Proprietary
License
Claude Opus 4.6
Proprietary
Claude Opus 4.7
Proprietary
Release date
Claude Opus 4.6
2026-02-01
Claude Opus 4.7
2026-04-16
If you are considering the documented upgrade path
- Deployment change
- Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Claude Opus 4.7 has the higher public score estimate, 72.33 versus 68.26, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.325 vs $0.325. Cache-heavy agent loop: $1.35 vs $1.35.
- Context tradeoff
- Both models list 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 evidence34 rows
Agentic
Terminal-Bench 2.0
Claude Opus 4.665.4%SourceClaude Opus 4.7—Not directly comparable
BrowseComp
Claude Opus 4.683.7%SourceClaude Opus 4.7—Not directly comparable
OSWorld-Verified
Claude Opus 4.672.7%SourceClaude Opus 4.7—Not directly comparable
Claw-Eval
Claude Opus 4.670.4%SourceClaude Opus 4.7—Not directly comparable
DeepSearchQA
Claude Opus 4.673.7%SourceClaude Opus 4.7—Not directly comparable
CyberGym
Claude Opus 4.666.6%SourceClaude Opus 4.7—Not directly comparable
Gert Labs
Shared sourceClaude Opus 4.661.85%Claude Opus 4.765.59%Claude Opus 4.7 leads this result
ResearchClawBench
Shared sourceClaude Opus 4.619.9%Claude Opus 4.720.7%Claude Opus 4.7 leads this result
JobBench
Claude Opus 4.636.7%SourceClaude Opus 4.7—Not directly comparable
OSWorld 2.0
Claude Opus 4.6—Claude Opus 4.713.9%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.680.8%SourceClaude Opus 4.7—Not directly comparable
SWE-bench Verified*
Claude Opus 4.675.6%SourceClaude Opus 4.7—Not directly comparable
LiveCodeBench Pro
Claude Opus 4.670.7%SourceClaude Opus 4.7—Not directly comparable
SWE-bench Pro
Claude Opus 4.653.4%SourceClaude Opus 4.7—Not directly comparable
SWE-Rebench
Claude Opus 4.665.3%SourceClaude Opus 4.7—Not directly comparable
React Native Evals
Shared sourceClaude Opus 4.684.1%Claude Opus 4.782.8%Claude Opus 4.6 leads this result
Vibe Code Bench
Shared sourceClaude Opus 4.657.57%Claude Opus 4.771.00%Claude Opus 4.7 leads this result
FrontierCode 1.1 Main
Shared sourceClaude Opus 4.626.9%Claude Opus 4.738.5%Claude Opus 4.7 leads this result
Knowledge
GPQA
Claude Opus 4.691.3%SourceClaude Opus 4.7—Not directly comparable
GPQA-D
Claude Opus 4.689.2%SourceClaude Opus 4.7—Not directly comparable
SuperGPQA
Claude Opus 4.695%SourceClaude Opus 4.7—Not directly comparable
MMLU-Pro
Claude Opus 4.682%SourceClaude Opus 4.7—Not directly comparable
MMLU-Pro (Arcee)
Claude Opus 4.689.1%SourceClaude Opus 4.7—Not directly comparable
HLE
Claude Opus 4.653%SourceClaude Opus 4.7—Not directly comparable
HLE w/o tools
Claude Opus 4.640%SourceClaude Opus 4.7—Not directly comparable
HealthBench Hard
Claude Opus 4.614.8%SourceClaude Opus 4.7—Not directly comparable
MedXpertQA (Text)
Claude Opus 4.652.1%SourceClaude Opus 4.7—Not directly comparable
Math
AIME25 (Arcee)
Claude Opus 4.699.8%SourceClaude Opus 4.7—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceClaude Opus 4.640.700%Claude Opus 4.743.793%Claude Opus 4.7 leads this result
FrontierMath v2 (Tier 4)
Shared sourceClaude Opus 4.622.900%Claude Opus 4.722.917%Claude Opus 4.7 leads this result
Multimodal
MMMU-Pro
Claude Opus 4.677.3%SourceClaude Opus 4.7—Not directly comparable
ERQA
Claude Opus 4.651.6%SourceClaude Opus 4.7—Not directly comparable
ScreenSpot Pro
Claude Opus 4.683.1%SourceClaude Opus 4.7—Not directly comparable
MedXpertQA (MM)
Claude Opus 4.664.8%SourceClaude Opus 4.7—Not directly comparable
Frequently asked questions
Which is better, Claude Opus 4.6 or Claude Opus 4.7?
Claude Opus 4.7 has the higher public score estimate, 72.33 versus 68.26, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Opus 4.6 or Claude Opus 4.7?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, Claude Opus 4.6 or Claude Opus 4.7?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Claude Opus 4.6 or Claude Opus 4.7?
For the stated presets, chat costs $0.0175 on Claude Opus 4.6 and $0.0175 on Claude Opus 4.7; repository review costs $0.325 and $0.325; the cache-heavy agent loop costs $1.35 and $1.35. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate. Claude Opus 4.7 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Opus 4.6 or Claude Opus 4.7?
Both models list the same context window, 1M.
Related comparisons
Last updated August 29, 2026
Watch Claude Opus 4.6 vs Claude Opus 4.7
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.