INTELLIGENCE
50.0
Media Cap quality axis
Microsoft · Open weightsmicrosoft/phi-4-reasoning-plus
Active
Model portfolio
microsoft/phi-4-reasoning-plus
Tap a star to rate
Microsoft · Open · Context 32K tokens
Language Cap
44
Cadle Language Cap 44 · 52%
Benchmark average
62.3
Not enough benchmark results yet
Pricing
$0.070
$0.35 / 1M out · 120.2 pts/$
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
50.0
Intelligence
No data yet
Coding
24.2
Agentic
No data yet
MMLU
76.0
GPQA
68.9
Math
81.3
LiveCodeBench
53.1
HumanEval
No data yet
Reason
84.9
ARC-AGI
No data yet
Coverage AVG
62.3
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
24.2
Media Cap quality axis
MATH
81.3
Media Cap quality axis
KNOWLEDGE
71.3
Media Cap quality axis
MATRIX OVERALL
50.0
AVG 62.3 across matrix cells
STRONGEST SIGNAL
Intelligence
Cap axis 50.0
BLENDED $/1M
$0.42
In $0.070 · Out $0.35
VALUE INDEX
119.0
Quality ÷ blended $/1M (higher is better)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 50.0
- Cap Intelligence
- 50.5
- Cap Coding
- 19.4
- Matrix Coding
- 24.2
- Input $/1M
- $0.070
- Output $/1M
- $0.35
- Value pts/$
- 120.19
DESCRIPTION + DETAILS
PROVIDER
Microsoft
CONTEXT
32K 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 microsoft/phi-4-reasoning-plus.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | Microsoft |
| Release | |
| Input / 1M | $0.07 |
| Output / 1M | $0.35 |
| Context | 32K tokens |
| Cadle Cap | 44 |
| Cap board | Cadle Language Cap 44 |
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.
Overall50
Coding24.2
MMLU76
GPQA68.9
Math81.3
LiveCodeBench53.1