Benchmark avg
47.1
5 tracked scores
ActiveModel portfolio
claude-sonnet-4-20250514_16K
Tap a star to rate
Anthropic · Closed · Context 200K tokens
Cadle Score
143.2
#103 in index
Benchmark average
—
Not enough benchmark results yet
Pricing
Unlisted
no list price
MODEL MATRIX · TRUTH CENTER CELLS
Overall
—
Intelligence
—
Coding
—
Reasoning
22.9
Language
81.4
Knowledge
—
Agentic
62.0
MMLU
—
GPQA
—
Math
—
LiveCodeBench
—
HumanEval
—
Reason
—
ARC-AGI
22.9
Coverage AVG
40.4
Pillar Coverage:3 / 7 Core Pillars (43%)
Cadle Cap ranks models with within-benchmark percentiles so ARC-AGI ~40 and MMLU ~90 never compete raw. Coverage AVG is an importance-weighted mean of filled expert cells only — blanks are skipped, not zeroed.
ANALYSIS · TRUTH CENTER
Hard benches (GPQA · ARC-AGI · LCB · Agentic) sit left — a mid-40 on ARC-AGI can still be frontier. Broader benches on the right are easier and often higher.
CADLE INSIGHTS
Only measured signals
Strongest signal
lech-mazur-writing
Score 81.4
Blended $/1M
Unlisted
No published list price
Context
200K
Provider context window (not max output)
Agentic
62.0
Tool-use / agentic matrix cell
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Cadle Score
- 143.2
DESCRIPTION + DETAILS
PROVIDER
Anthropic
CONTEXT
200K tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
Community Reviews & Field Notes
Verified EngineersReal operator evaluations, prompt robustness observations, and deployment notes for claude-sonnet-4-20250514_16K.
4.5(2)
Leave a Field Observation
Rating:5 - Frontier benchmark
Role:
Tag topic:
Reviews are publicly visible to the engineering community.
Inference OperatorProduction Deployer Verified
Oct 31, 2026
Tested claude-sonnet-4-20250514_16K on high-concurrency tool loops. Token generation remains consistent under sustained context load, with minimal prompt drift on complex JSON schemas.
Autonomous Agent LeadEval Maintainer Verified
Oct 27, 2026
Evaluated claude-sonnet-4-20250514_16K on multi-turn code synthesis. Code reasoning and diff application succeed on ~88% of test suites. Best paired with strict system prompt guardrails.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | Anthropic |
| Release | |
| Input / 1M | No data yet |
| Output / 1M | No data yet |
| Context | 200K tokens |
| Cadle Cap | 143 |
| Cap board | Cadle Language Cap 143 |
| arc-agi-2 | 5.9 |
| arc-agi | 40.0 |
| lech-mazur-writing | 81.4 |
| metr-time-horizons | 62.0 |
| weirdml | 46.1 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Agentic62
ARC-AGI22.9