Matrix overall
75.0
AVG 64.0 across matrix cells
ActiveModel portfolio
Qwen-14B
Tap a star to rate
Alibaba · Open
Cadle Score
112.9
#29 in index
Benchmark average
64.0
Not enough benchmark results yet
Pricing
$0.070
$0.070 / 1M out · 535.7 pts/$
MODEL MATRIX · TRUTH CENTER CELLS
Overall
75.0
Intelligence
75.0
Coding
—
Reasoning
79.2
Language
55.5
Knowledge
57.5
Agentic
—
MMLU
55.1
GPQA
—
Math
61.3
LiveCodeBench
—
HumanEval
—
Reason
79.2
ARC-AGI
—
Coverage AVG
64.0
Pillar Coverage:5 / 7 Core Pillars (71%)
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
62.8
8 tracked scores
Strongest signal
epoch-eci
Score 112.9
Blended $/1M
$0.14
In $0.070 · Out $0.070
Value index
535.7
Quality ÷ blended $/1M (higher is better)
Intel index
75.0
Matrix AA IQ cell
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Cadle Score
- 112.9
- Overall (Matrix)
- 75.0
- Cadle Intelligence
- 75.0
- Input $/1M
- $0.070
- Output $/1M
- $0.070
- Value pts/$
- 535.71
DESCRIPTION + DETAILS
PROVIDER
Alibaba
STATUS
ACTIVE
COMMUNITY REVIEWS
Community Reviews & Field Notes
Verified EngineersReal operator evaluations, prompt robustness observations, and deployment notes for Qwen-14B.
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 1, 2026
Tested Qwen-14B 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 28, 2026
Evaluated Qwen-14B 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 | Alibaba |
| Release | |
| Input / 1M | $0.07 |
| Output / 1M | $0.07 |
| Context | No data yet |
| Cadle Cap | 113 |
| Cap board | Cadle Language Cap 113 |
| training-compute-flops | 23.4 |
| piqa | 59.8 |
| mmlu | 55.1 |
| lambada | 71.1 |
| gsm8k | 61.3 |
| bbh | 40.0 |
| arc-ai2 | 79.2 |
| epoch-eci | 112.9 |
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
Alibaba listing
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall75
AA IQ75
MMLU55.1
Math61.3