INTELLIGENCE
8.6
Media Cap quality axis
Anthropic · ProprietaryClaude 3 Haiku
Active
Model portfolio
Claude 3 Haiku
Tap a star to rate
Anthropic · Released 2024-03-04 · v2024-03-04 · Closed · Context 200K tokens
Language Cap
22
Cadle Language Cap 22 · 77%
Benchmark average
42.7
Not enough benchmark results yet
Pricing
$0.25
$1.25 / 1M out · 3.9 pts/$
CADLE CAP vs MODEL MATRIX
Cadle Cap ranks models on every published score we have for them — harder benchmarks weigh more. Missing tests are skipped, not zeroed. It answers who is stronger than whom in today's pool.
Model Matrix is the datasheet: Overall, Intelligence, Coding, Agentic, MMLU, GPQA, Math, LiveCodeBench, HumanEval, Reason, ARC-AGI. A dash means unmeasured. AVG is an importance-weighted mean of that model's filled cells only.
MODEL MATRIX · TRUTH CENTER CELLS
Overall
13.9
Intelligence
5.6
Coding
No data yet
Agentic
48.5
MMLU
72.8
GPQA
37.4
Math
57.4
LiveCodeBench
15.4
HumanEval
No data yet
Reason
40.1
ARC-AGI
No data yet
Coverage AVG
42.7
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
CODING
15.4
Media Cap quality axis
AGENTIC
48.5
Media Cap quality axis
MATH
57.4
Media Cap quality axis
MATRIX OVERALL
13.9
AVG 42.7 across matrix cells
STRONGEST SIGNAL
Intelligence
Cap axis 8.6
BLENDED $/1M
$1.50
In $0.25 · Out $1.25
VALUE INDEX
9.3
Quality ÷ blended $/1M (higher is better)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 13.9
- Cap Intelligence
- 5.9
- AA / Intel index
- 5.6
- Cap Coding
- 15.4
- Input $/1M
- $0.25
- Output $/1M
- $1.25
- Value pts/$
- 3.93
DESCRIPTION + DETAILS
PROVIDER
Anthropic
RELEASE
2024-03-04
CONTEXT
200K tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — not marketing copy.
No reviews yet
WRITE A REVIEW
Tap a star to rate
Stored on this device · synced when signed in
No operator notes yet
First review sets the tone for how teams evaluate Claude 3 Haiku.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | Anthropic |
| Release | 2024-03-04 |
| Input / 1M | $0.25 |
| Output / 1M | $1.25 |
| Context | 200K tokens |
| Cadle Cap | 22 |
| Cap board | Cadle Language Cap 22 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
Anthropic listing
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall13.9
AA IQ5.6
Agentic48.5
MMLU72.8
GPQA37.4
Math57.4
LiveCodeBench15.4