Benchmark avg
35.4
15 tracked scores
Microsoft · Open weightsPhi-2
Active
Model portfolio
Phi-2
Tap a star to rate
Microsoft · Open
Language Cap
59
Cadle Language Cap 59 · 39%
Benchmark average
—
Not enough benchmark results yet
Pricing
Unlisted
no list price
MODEL MATRIX · TRUTH CENTER CELLS
Overall
—
Intelligence
60.7
Coding
—
Agentic
—
MMLU
—
GPQA
—
Math
—
LiveCodeBench
—
HumanEval
—
Reason
—
ARC-AGI
—
Coverage AVG
—
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.
CADLE INSIGHTS
Only measured signals
Strongest signal
epoch-eci
Score 107.7
Blended $/1M
Unlisted
No published list price
Intel index
60.7
Matrix AA IQ cell
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Cadle Intelligence
- 60.7
DESCRIPTION + DETAILS
PROVIDER
Microsoft
STATUS
ACTIVE
COMMUNITY REVIEWS
Community Reviews & Field Notes
Verified EngineersReal operator evaluations, prompt robustness observations, and deployment notes for Phi-2.
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 27, 2026
Tested Phi-2 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 23, 2026
Evaluated Phi-2 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 | Microsoft |
| Release | |
| Input / 1M | No data yet |
| Output / 1M | No data yet |
| Context | No data yet |
| Cadle Cap | 59 |
| Cap board | Cadle Language Cap 59 |
| mmlu-pro | 18.1 |
| musr | 13.8 |
| gpqa-diamond | 2.9 |
| math-level-5 | 2.9 |
| bbh | 28.0 |
| ifeval | 27.4 |
| winogrande | 9.4 |
| openbookqa | 64.8 |
| mmlu | 44.5 |
| anli | 13.8 |
| hellaswag | 38.1 |
| triviaqa | 45.2 |
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 IQ60.7