SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- AA / Intel index
- 5.8
- Input $/1M
- $0.050
- Output $/1M
- $0.10
- Value pts/$
- 38.67
Microsoft · Open weightsmicrosoft/Phi-4-multimodal-instruct
Active
Model portfolio
microsoft/Phi-4-multimodal-instruct
Tap a star to rate
Microsoft · Released 2025-02-26 · v2025-02-26 · Open · Context 128K tokens
Language Cap
No data yet
language · unranked
Vision Cap
85
#81/268
Benchmark average
35.2
Not enough benchmark results yet
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
5.8
Coding
No data yet
Agentic
No data yet
MMLU
31.5
GPQA
31.5
Math
69.3
LiveCodeBench
13.1
HumanEval
No data yet
Reason
No data yet
ARC-AGI
No data yet
Coverage AVG
35.2
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.
DESCRIPTION + DETAILS
PROVIDER
Microsoft
RELEASE
2025-02-26
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 microsoft/Phi-4-multimodal-instruct.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | Microsoft |
| Release | 2025-02-26 |
| Input / 1M | $0.05 |
| Output / 1M | $0.10 |
| Context | 128K tokens |
| Cadle Cap | 53 |
| Cap board | Unranked |
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 IQ5.8
MMLU31.5
GPQA31.5
Math69.3
LiveCodeBench13.1