CADLE CAP
95
Cadle #14/385 · 70% confidence
Moonshot AI · ProprietaryMoonshotAI: Kimi K3.1 Pro
Active
Model portfolio
MoonshotAI: Kimi K3.1 Pro
Tap a star to rate
Moonshot AI · Released 2026-10-23 · v2026-10-23 · Closed · Context 1.0M tokens
MoonshotAI: Kimi K3.1 Pro is a closed model from Moonshot AI (released 2026-10-23). Context window ~1.0M tokens with capabilities: Vision, Video, Text. Positioned for higher-effort reasoning workloads. List pricing ≈ $2.00 / $10.00 per 1M input/output tokens. Top tracked signals: REASON · benchlm 98.0, REASON 98.0, GPQA · benchlm 94.2. Cadle merges provider listings, unified leaderboard medians, and public pricing where available.
Language Cap
95
Cadle Language #14/385 · 70%
Benchmark average
81.8
#60 on the benchmark matrix
Pricing
$2.00
$10.00 / 1M out · 8.2 pts/$
CROSS-BOARD RANKS
Cadle Language LLM #14/385Matrix #60/443AA #5/698vs AA: +8
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
—
AA IQ
55.1
Coding
77.1
Agentic
79.6
MMLU
91.0
GPQA
94.2
Math
—
LiveCodeBench
60.8
HumanEval
—
Reason
98.0
ARC-AGI
—
Coverage AVG
81.8
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
55.1
Media Cap quality axis
CODING
77.1
Media Cap quality axis
AGENTIC
79.6
Media Cap quality axis
KNOWLEDGE
93.1
Media Cap quality axis
BENCHMARK AVG
78.3
16 tracked scores
STRONGEST SIGNAL
REASON · benchlm
Score 98.0
BLENDED $/1M
$12.00
In $2.00 · Out $10.00
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Cap Intelligence
- 98.1
- AA / Intel index
- 55.1
- Cap Coding
- 86.4
- Matrix Coding
- 77.1
- Speed tok/s
- 66
- Latency
- 1.9 s
- Input $/1M
- $2.00
- Output $/1M
- $10.00
- Value pts/$
- 8.18
DESCRIPTION + DETAILS
MoonshotAI: Kimi K3.1 Pro is a closed model from Moonshot AI (released 2026-10-23). Context window ~1.0M tokens with capabilities: Vision, Video, Text. Positioned for higher-effort reasoning workloads. List pricing ≈ $2.00 / $10.00 per 1M input/output tokens. Top tracked signals: REASON · benchlm 98.0, REASON 98.0, GPQA · benchlm 94.2. Cadle merges provider listings, unified leaderboard medians, and public pricing where available.
PROVIDER
Moonshot AI
RELEASE
2026-10-23
CONTEXT
1.0M 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 MoonshotAI: Kimi K3.1 Pro.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | Moonshot AI |
| Release | 2026-10-23 |
| Input / 1M | $2.00 |
| Output / 1M | $10.00 |
| Context | 1.0M tokens |
| Cadle Cap | 95 |
| Cap board | Cadle Language #14/385 |
| REASON · benchlm | 98.0 |
| REASON | 98.0 |
| GPQA · benchlm | 94.2 |
| GPQA | 94.2 |
| AGENTIC · benchlm | 92.1 |
| MMLU · benchlm | 91.0 |
| MMLU | 91.0 |
| AGENTIC | 79.6 |
| CODING · benchlm | 77.1 |
| CODING | 77.1 |
| AGENTIC · artificial-analysis | 67.2 |
| LIVECODEBENCH · benchlm | 60.8 |
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)
- Artificial Analysis — throughput, latency, and $/M token snapshots
- Epoch AI Benchmarking Hub — capability CSV exports (when synced)
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
Moonshot AI listing
API
artificial-analysis
API
OpenRouter
COMMUNITY
Papers with Code
COMMUNITY
BenchLM
COMMUNITY
unified-median
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
AA IQ55.1
Coding77.1
Agentic79.6
MMLU91
GPQA94.2
LiveCodeBench60.8
AA Index55.1