none reviewed yet · 2 benchmark observations · latest capture Sep 8, 2026
Inspect the evidenceAnthropic · MODEL PROFILE
Claude Opus 4.8
Backend-heavy repo work where SWE-bench-style correctness matters more than UI taste
Saved editorial fit for your current task lens; not a benchmark result
How scoring worksVerified rates (Sep 8, 2026) · 100 runs / month at your token settings
Adjust workloadAt a glance
9 facts- Provider
- Anthropic
- Type
- API model
- Access
- Anthropic API, AWS Bedrock, Claude Code
- Context
- 1,000,000 tokens
- Maximum output
- 128K tokens
- License / weights
- Proprietary
- Input modalities
- text, image, file
- Output modalities
- text
- Pricing notes
- $5 in / $25 out per 1M; cache read $0.50, cache write $6.25
The practical trade-offs
Documented strengths
- SWE-bench Verified 88.6% and Pro 69.2% remain top-10 results
- NL2Repo 69.7 is the highest in DeepSeek's and Z.ai's published comparison tables
- Deeply sampled Arena row (9,804 votes)
- Lower TTFT (42 s) than the Fable tier
Limitations to check
- Design Arena Website 1269 (rank 33) shows weak visual preference relative to its code strength
- Legacy status on Anthropic's pricing page
- Same $5/$25 price as the much stronger Opus 5
- Arena effort aliases differ by 23 Elo
Follow the source
7 source linksEvidence & conditions
7Source links
NoneReviewed records
2Benchmark runs
Sep 8, 2026Latest capture
- Evidence source 1
docs.aws.amazon.comDate not recorded - Evidence source 2
anthropic.comDate not recorded - Evidence source 3
arena.aiDate not recorded - Evidence source 4
benchlm.aiDate not recorded - Evidence source 5
benchlm.aiDate not recorded - Evidence source 6
artificialanalysis.aiDate not recorded - Evidence source 7
huggingface.coDate not recorded
Benchmark observations
SWE-bench Verified Inspect conditions
- name
- SWE-bench Verified
- value
- 88.6
- unit
- %
- source Url
- https://www-cdn.anthropic.com/0b4915911bb0d19eca5b5ee635c80fef830a37ea.pdf
- checked At
- 2026-09-08T19:30:56Z
- attribution
- provider-reported
- configuration
- Section 8.2: 500 tasks, 5 trials, adaptive thinking, max effort, default sampling. Verified in primary-source search extraction; PDF download failed.
SWE-bench Pro Inspect conditions
- name
- SWE-bench Pro
- value
- 69.2
- unit
- %
- source Url
- https://www-cdn.anthropic.com/0b4915911bb0d19eca5b5ee635c80fef830a37ea.pdf
- checked At
- 2026-09-08T19:30:56Z
- attribution
- provider-reported
- configuration
- Section 8.2: 5 trials, adaptive thinking, max effort, default sampling. Primary-source search extraction; PDF download failed.
Source reports, measured results, and editorial assessments are separate evidence types. Source dates do not imply a new benchmark run. Capture dates are shown when recorded; otherwise we say the capture date was not recorded. Recorded dates are compared with this catalogue snapshot (Sep 11, 2026), not today’s date.
Method AIS-V2
How this page is assessed
Quality claims follow Method AIS-V2.
Money never buys rank — commercial relationships cannot change rank, eligibility, evidence quality, or publication timing.
Submit or claim a listing is free and does not skip the editorial queue.
Private · this device only