INTELLIGENCE
7.8
Media Cap quality axis
Ant Group · ProprietaryLing-flash-2.0
Active
Model portfolio
Ling-flash-2.0
Tap a star to rate
Ant Group · Released 2025-09-17 · v2025-09-17 · Closed · Context 131K tokens
Language Cap
34
Cadle Language Cap 34 · 59%
Benchmark average
54.0
Not enough benchmark results yet
Pricing
$0.14
$0.57 / 1M out · 36.5 pts/$
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
No data yet
Intelligence
7.8
Coding
No data yet
Agentic
20.8
MMLU
77.7
GPQA
65.7
Math
65.3
LiveCodeBench
58.9
HumanEval
No data yet
Reason
34.4
ARC-AGI
No data yet
Coverage AVG
54.0
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
CODING
58.9
Media Cap quality axis
AGENTIC
20.8
Media Cap quality axis
MATH
65.3
Media Cap quality axis
STRONGEST SIGNAL
Intelligence
Cap axis 7.8
BLENDED $/1M
$0.71
In $0.14 · Out $0.57
VALUE INDEX
76.1
Quality ÷ blended $/1M (higher is better)
CONTEXT
131K
Provider context window (not max output)
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Cap Intelligence
- 25.9
- Cadle Intelligence
- 7.8
- Cap Coding
- 73.1
- Input $/1M
- $0.14
- Output $/1M
- $0.57
- Value pts/$
- 36.53
DESCRIPTION + DETAILS
PROVIDER
Ant Group
RELEASE
2025-09-17
CONTEXT
131K tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — verified production observations.
4.5
2 notes indexed
SUBMIT OPERATOR NOTE
Tap a star to rate
Topic:
5 - Frontier benchmark
Stored locally · synced to your profile
I
Inference Operator
VerifiedOct 23, 2026
Tested Ling-flash-2.0 on high-concurrency tool loops. Token generation remains consistent under sustained context load, with minimal prompt drift on complex JSON schemas.
A
Autonomous Agent Lead
VerifiedOct 19, 2026
Evaluated Ling-flash-2.0 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 |  Ling-flash-2.0 |
|---|---|
| Provider | Ant Group |
| Release | 2025-09-17 |
| Input / 1M | $0.14 |
| Output / 1M | $0.57 |
| Context | 131K tokens |
| Cadle Cap | 34 |
| Cap board | Cadle Language Cap 34 |
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.
AA IQ7.8
Agentic20.8
MMLU77.7
GPQA65.7
Math65.3
LiveCodeBench58.9