Matrix overall
60.0
AVG 48.9 across matrix cells
ActiveModel portfolio
DeepSeek-Coder-V2-Lite-Base
Tap a star to rate
DeepSeek · Open
Cadle Score
108.7
#37 in index
Benchmark average
48.9
Not enough benchmark results yet
Pricing
Unlisted
no list price
MODEL MATRIX · TRUTH CENTER CELLS
Overall
60.0
Intelligence
60.0
Coding
30.6
Reasoning
43.1
Language
45.8
Knowledge
47.3
Agentic
—
MMLU
47.3
GPQA
—
Math
67.1
LiveCodeBench
—
HumanEval
—
Reason
43.1
ARC-AGI
—
Coverage AVG
48.9
Pillar Coverage:6 / 7 Core Pillars (86%)
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
57.1
6 tracked scores
Strongest signal
epoch-eci
Score 108.7
Blended $/1M
Unlisted
No published list price
Coding (matrix)
30.6
Model Matrix coding cell
Intel index
60.0
Matrix AA IQ cell
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Cadle Score
- 108.7
- Overall (Matrix)
- 60.0
- Cadle Intelligence
- 60.0
- Matrix Coding
- 30.6
DESCRIPTION + DETAILS
PROVIDER
DeepSeek
STATUS
ACTIVE
COMMUNITY REVIEWS
Community Reviews & Field Notes
Verified EngineersReal operator evaluations, prompt robustness observations, and deployment notes for DeepSeek-Coder-V2-Lite-Base.
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
Nov 2, 2026
Tested DeepSeek-Coder-V2-Lite-Base 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 29, 2026
Evaluated DeepSeek-Coder-V2-Lite-Base 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 | DeepSeek |
| Release | |
| Input / 1M | No data yet |
| Output / 1M | No data yet |
| Context | No data yet |
| Cadle Cap | 109 |
| Cap board | Cadle Language Cap 109 |
| bigcodebench | 30.6 |
| winogrande | 45.8 |
| mmlu | 47.3 |
| gsm8k | 67.1 |
| arc-ai2 | 43.1 |
| epoch-eci | 108.7 |
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.
Overall60
AA IQ60
Coding30.6
MMLU47.3
Math67.1
TECHNICAL FIELD GUIDESAll 10 Guides →