CADLE CAP
92
Cadle #26/385 · 84% confidence
Google · Proprietarygoogle/gemini-3.1-pro
Active
Model portfolio
google/gemini-3.1-pro
Tap a star to rate
Google · Closed
google/gemini-3.1-pro is a closed model from Google. Context window size is not listed with capabilities: Text, Vision, Reasoning. Positioned for higher-effort reasoning workloads. List pricing ≈ $2.00 / $12.00 per 1M input/output tokens. Top tracked signals: AGENTIC · benchlm 100.0, AGENTIC 100.0, GPQA · epoch 96.5. Cadle merges provider listings, unified leaderboard medians, and public pricing where available.
Language Cap
92
Cadle Language #26/385 · 84%
Benchmark average
86.8
#18 on the benchmark matrix
Pricing
$2.00
$12.00 / 1M out · 6.6 pts/$
CROSS-BOARD RANKS
Cadle Language LLM #26/385Matrix #18/443BenchLM #38/224vs BenchLM: -14
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
64.7
AA IQ
69.6
Coding
77.3
Agentic
100.0
MMLU
93.2
GPQA
96.0
Math
80.3
LiveCodeBench
88.5
HumanEval
—
Reason
82.0
ARC-AGI
77.1
Coverage AVG
86.8
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
INTELLIGENCE
67.9
Media Cap quality axis
CODING
77.3
Media Cap quality axis
AGENTIC
100.0
Media Cap quality axis
MATH
80.3
Media Cap quality axis
MATRIX OVERALL
64.7
AVG 86.8 across matrix cells
BENCHMARK AVG
83.1
23 tracked scores
STRONGEST SIGNAL
AGENTIC · benchlm
Score 100.0
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 64.7
- Cap Intelligence
- 93.0
- AA / Intel index
- 69.6
- Cap Coding
- 87.0
- Matrix Coding
- 77.3
- Input $/1M
- $2.00
- Output $/1M
- $12.00
- Value pts/$
- 6.64
DESCRIPTION + DETAILS
google/gemini-3.1-pro is a closed model from Google. Context window size is not listed with capabilities: Text, Vision, Reasoning. Positioned for higher-effort reasoning workloads. List pricing ≈ $2.00 / $12.00 per 1M input/output tokens. Top tracked signals: AGENTIC · benchlm 100.0, AGENTIC 100.0, GPQA · epoch 96.5. Cadle merges provider listings, unified leaderboard medians, and public pricing where available.
PROVIDER
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 google/gemini-3.1-pro.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | |
| Release | |
| Input / 1M | $2.00 |
| Output / 1M | $12.00 |
| Context | — |
| Cadle Cap | 92 |
| Cap board | Cadle Language #26/385 |
| AGENTIC · benchlm | 100.0 |
| AGENTIC | 100.0 |
| GPQA · epoch | 96.5 |
| GPQA | 96.0 |
| MATH · epoch | 95.6 |
| GPQA · benchlm | 95.5 |
| MMLU · benchlm | 93.2 |
| MMLU | 93.2 |
| LIVECODEBENCH · benchlm | 88.5 |
| LIVECODEBENCH | 88.5 |
| REASON · benchlm | 82.0 |
| REASON | 82.0 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- OpenRouter / provider APIs (pricing & context)
- Hugging Face Hub (downloads & cards)
- Papers With Code (task benchmarks)
- BenchLM.ai (category rollups + atomic benches)
- Epoch AI Benchmarking Hub (ECI + ZIP CSVs)
- LiveCodeBench (generation / execution / repair / test-output)
- Artificial Analysis (intelligence / indexes)
- LLM Stats (leaderboard + rankings)
- Cadle unified median (equal-weight multi-source)
- Epoch AI Benchmarking Hub — capability CSV exports (when synced)
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
Google listing
API
OpenRouter
COMMUNITY
Papers with Code
COMMUNITY
BenchLM
COMMUNITY
unified-median
COMMUNITY
epoch
COMMUNITY
llm-stats
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall64.7
AA IQ69.6
Coding77.3
Agentic100
MMLU93.2
GPQA96
Math80.3
LiveCodeBench88.5
ARC-AGI77.1