none reviewed yet · 0 benchmark observations · latest capture Sep 8, 2026
Inspect the evidenceAnthropic · MODEL PROFILE
Claude Sonnet 5
Teams that need Claude-grade code quality across a whole org at moderate cost
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, Claude apps (including Free plan), 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
- $2 in / $10 out per 1M; cache read $0.20, cache write $2.50
The practical trade-offs
Documented strengths
- SWE-bench Verified 85.2% at $2/$10 is the best correctness-per-dollar in the Anthropic line
- 1M multimodal context and 128K output at mid-tier price
- Only Claude in this set available on the consumer Free plan
- Well-sampled Arena row (7,006 votes)
Limitations to check
- TTFT 203.67 s at max effort is among the worst measured here
- Design Arena 1292 and Arena 1543 are mid-pack visually
- Anthropic docs give no separate Sonnet-5 frontend claims
- Several AA effort variants have no published score
Follow the source
6 source linksEvidence & conditions
6Source links
NoneReviewed records
NoneBenchmark 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
No comparable benchmark observations are recorded for this entry.
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