Model Profile
anthropic/claude-sonnet-4-5-20250929-thinking
Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.
Identity
ID: external/anthropic/claude-sonnet-4-5-20250929-thinking
Author: anthropic
Origin: external_benchmark_shadow
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 26.6%
Evidence points: 211
Raw rows: 465
Weighted rows: 20
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 0
Intelligence Profile
Dimension Breakdown
No eq benchmarks found
No accuracy benchmarks found
No creativity benchmarks found
No based benchmarks found
1/5 dimensions scored · Last updated Apr 19, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
Vals Legal Bench
overall_accuracy_pct
Normalized value 93.0% · confidence 100.0%
Strongest impact in Contract Drafting & Redlining
vals_legal_bench.overall_accuracy_pct · Mar 31, 2026
Vals Finance Agent
overall_accuracy_pct
Normalized value 86.0% · confidence 100.0%
Strongest impact in Thesis red teaming
vals_finance_agent.overall_accuracy_pct · Mar 31, 2026
Vals CorpFin v2
overall_accuracy_pct
Normalized value 81.8% · confidence 100.0%
Strongest impact in Thesis red teaming
vals_corp_fin_v2.overall_accuracy_pct · Mar 31, 2026
Vals Case Law v2
overall_accuracy_pct
Normalized value 56.6% · confidence 100.0%
Strongest impact in Contract Drafting & Redlining
vals_case_law_v2.overall_accuracy_pct · Mar 31, 2026
Vals Tax Eval v2
overall_accuracy_pct
Normalized value 89.2% · confidence 100.0%
Strongest impact in Accounts payable invoice extraction (text)
vals_tax_eval_v2.overall_accuracy_pct · Mar 31, 2026
Vals SWE-bench
overall_accuracy_pct
Normalized value 80.5% · confidence 100.0%
Strongest impact in Simulation setup assistant
vals_swebench.overall_accuracy_pct · Mar 31, 2026
Some fit rows have limited benchmark evidence.
5 of 12 scored use cases have low confidence or thin contributor coverage.
Coverage Diagnostics
actively scoredUse-Case Scores
120
Total Measurements
465
Weighted Measurements
20
Weighted Sources
14
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Thesis red teaming use_case.fin.thesis_red_team | 27.0% |
| Accounts payable invoice extraction (text) use_case.fin.ap_invoice_extraction | 25.7% |
| Earnings call synthesis use_case.fin.earnings_call_synthesis | 24.4% |
| Transaction anomaly narrative use_case.fin.transaction_anomaly_narrative | 23.9% |
| KYC profile synthesis use_case.fin.kyc_profile_synthesis | 23.0% |
| AML alert triage use_case.fin.aml_alert_triage | 23.0% |
| Filings summarization (10-K/10-Q) use_case.fin.filings_summarization | 21.3% |
| Quant research code generation use_case.fin.alpha_research_codegen | 18.8% |
| Simulation setup assistant use_case.eng.simulation_setup_assistant | 17.5% |
| Component selection assistant use_case.eng.component_selection | 17.0% |
| Contract Drafting & Redlining use_case.legal.contract_drafting | 15.4% |
| Literature synthesis with citations use_case.bio.literature_synthesis | 15.3% |