INTELLIGENCE
6.3
Media Cap quality axis
Microsoft · Open weightsPhi-4 Mini Instruct
Active
Model portfolio
Phi-4 Mini Instruct
Tap a star to rate
Microsoft · Released 2024-02-26 · v2024-02-26 · Open · Context 128K tokens
Language Cap
16
Cadle Language Cap 16 · 59%
Benchmark average
31.2
Not enough benchmark results yet
Pricing
$0.17
$0.68 / 1M out · 15.4 pts/$
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
No data yet
Intelligence
6.3
Coding
3.8
Agentic
37.0
MMLU
46.5
GPQA
33.1
Math
69.6
LiveCodeBench
12.6
HumanEval
No data yet
Reason
21.1
ARC-AGI
No data yet
Coverage AVG
31.2
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
3.8
Media Cap quality axis
AGENTIC
37.0
Media Cap quality axis
MATH
69.6
Media Cap quality axis
STRONGEST SIGNAL
Intelligence
Cap axis 6.3
BLENDED $/1M
$0.85
In $0.17 · Out $0.68
VALUE INDEX
36.7
Quality ÷ blended $/1M (higher is better)
CONTEXT
128K
Provider context window (not max output)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Cap Intelligence
- 13.1
- AA / Intel index
- 6.3
- Cap Coding
- 0.8
- Matrix Coding
- 3.8
- Input $/1M
- $0.17
- Output $/1M
- $0.68
- Value pts/$
- 15.45
DESCRIPTION + DETAILS
PROVIDER
Microsoft
RELEASE
2024-02-26
CONTEXT
128K 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 Phi-4 Mini Instruct.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | Microsoft |
| Release | 2024-02-26 |
| Input / 1M | $0.17 |
| Output / 1M | $0.68 |
| Context | 128K tokens |
| Cadle Cap | 16 |
| Cap board | Cadle Language Cap 16 |
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
Microsoft listing
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
AA IQ6.3
Coding3.8
Agentic37
MMLU46.5
GPQA33.1
Math69.6
LiveCodeBench12.6