Matrix overall
82.8
AVG 82.8 across matrix cells
ActiveModel portfolio
Gemini 2.5 Pro Preview (May' 25)
Tap a star to rate
Google · Released 2025-05-06 · v2025-05-06 · Closed
Cadle Score
—
Unranked · 74%
Benchmark average
—
Not enough benchmark results yet
Pricing
Unlisted
no list price
MODEL MATRIX · TRUTH CENTER CELLS
Overall
82.8
Intelligence
—
Coding
82.8
Reasoning
—
Language
—
Knowledge
—
Agentic
—
MMLU
—
GPQA
—
Math
—
LiveCodeBench
82.8
HumanEval
—
Reason
—
ARC-AGI
—
Coverage AVG
82.8
Pillar Coverage:1 / 7 Core Pillars (14%)
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
Benchmark avg
82.8
1 tracked scores
Strongest signal
livecodebench
Score 82.8
Blended $/1M
Unlisted
No published list price
Coding (matrix)
82.8
Model Matrix coding cell
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Overall (Matrix)
- 82.8
- Matrix Coding
- 82.8
DESCRIPTION + DETAILS
PROVIDER
RELEASE
2025-05-06
STATUS
ACTIVE
COMMUNITY REVIEWS
Community Reviews & Field Notes
Verified EngineersReal operator evaluations, prompt robustness observations, and deployment notes for Gemini 2.5 Pro Preview (May' 25).
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 31, 2026
Tested Gemini 2.5 Pro Preview (May' 25) 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 27, 2026
Evaluated Gemini 2.5 Pro Preview (May' 25) 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 | |
| Release | 2025-05-06 |
| Input / 1M | No data yet |
| Output / 1M | No data yet |
| Context | No data yet |
| Cadle Cap | 82 |
| Cap board | Unranked |
| livecodebench | 82.8 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall82.8
Coding82.8
LiveCodeBench82.8