Matrix overall
62.7
AVG 63.0 across matrix cells
ActiveModel portfolio
Qwen2.5-Coder-3B
Tap a star to rate
Alibaba · Open · Context 32K tokens
Cadle Score
107.5
#28 in index
Benchmark average
63.0
Not enough benchmark results yet
Pricing
Unlisted
no list price
MODEL MATRIX · TRUTH CENTER CELLS
Overall
62.7
Intelligence
62.7
Coding
—
Reasoning
37.2
Language
48.0
Knowledge
—
Agentic
—
MMLU
—
GPQA
—
Math
75.7
LiveCodeBench
—
HumanEval
—
Reason
37.2
ARC-AGI
—
Coverage AVG
63.0
Pillar Coverage:4 / 7 Core Pillars (57%)
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
63.3
5 tracked scores
Strongest signal
epoch-eci
Score 107.5
Blended $/1M
Unlisted
No published list price
Context
32K
Provider context window (not max output)
Intel index
62.7
Matrix AA IQ cell
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Cadle Score
- 107.5
- Overall (Matrix)
- 62.7
- Cadle Intelligence
- 62.7
DESCRIPTION + DETAILS
PROVIDER
Alibaba
CONTEXT
32K tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
Community Reviews & Field Notes
Verified EngineersReal operator evaluations, prompt robustness observations, and deployment notes for Qwen2.5-Coder-3B.
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 Qwen2.5-Coder-3B 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 Qwen2.5-Coder-3B 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 | No data yet |
| Output / 1M | No data yet |
| Context | 32K tokens |
| Cadle Cap | 108 |
| Cap board | Cadle Language Cap 108 |
| winogrande | 34.8 |
| hellaswag | 61.2 |
| gsm8k | 75.7 |
| arc-ai2 | 37.2 |
| epoch-eci | 107.5 |
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.
Overall62.7
AA IQ62.7
Math75.7