AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#418

Ling 3.0 Tiny

Inclusionai Release: 2026-08-07 Tested on: 2026-10-01 02:53 inclusionai/ling-3.0-tiny::low
7.9B total (1.3B active)MoEOpen source
(high) (medium) (low) (default)

Summary

Ling 3.0 Tiny scores 3.7 on AI BENCHY and ranks #418. It has 9.6 reliability, a 18.8% pass rate, $0.000 total cost, and 63.15s average response time.

What makes Ling 3.0 Tiny unique: It stands out most in Anti-AI Tricks, where it ranks #1, while Data parsing and extraction is its weakest area at #7. Its total benchmark cost is unusually low for its score range.

Model facts

Researched on 2026-08-12

Reported
Parameters
7.9B total (1.3B active)
Architecture
MoE
Availability
Open source
License
MIT
Parameter source Availability source

Score

3.7

Consistency

9.7

Reliability

9.6

Total Cost (Current Price)

$0.000

Total Output Tokens

868,004

Total Input Tokens

99,662

Input Price

$0.000 / 1M

Output Price

$0.000 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 19

Attempt pass rate: 18.8%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

63.15s

Response Time (max): 252.08s

Response Time (total): 1389.35s

No answer: 7 Wrong answer: 5 Did not follow instructions: 4 API error: 2 Invalid tool call: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#418 Ling 3.0 Tiny

low
No output was saved. The original provider response or failure reason is unavailable.
Cost
$0.000
Time
200.0s
Tokens
5,030 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 02:53 Re-test 3.7 9.6 $0.000 Current run
2026-08-07 23:06 First recorded run 3.8 9.7 $0.000 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 02:53 · Current run69/69 attempts3.79.79.64/231868,00499,662$0.00063.15s
2026-08-07 23:06 · First recorded run66/66 attempts3.89.79.74/221977,83699,842$0.00066.85s
Difference—-0.20.0-0.100-109832-180$0.000-3697ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Ling 3.0 TinylowvsLing 3.0 TinyhighLing 3.0 TinylowvsLing 3.0 TinymediumLing 3.0 TinylowvsXing4.0 29b A4bmediumFree AvailableLing 3.0 TinylowvsGrok 4.20noneLing 3.0 TinylowvsNemotron 3.5 LightningnoneFree AvailableLing 3.0 TinylowvsCommand A+mediumLing 3.0 TinylowvsGranite 4.1 8bdefaultLing 3.0 TinylowvsXing4.0 29b A4bnoneFree AvailableLing 3.0 TinylowvsLing 3.0 TinydefaultLing 3.0 TinylowvsCommand A+high

Category Breakdown

Category Score Consistency Tests Correct
Agentic 3.0 10.0
Anti-AI Tricks 6.5 10.0
Coding 2.9 10.0
Combined 3.0 10.0
Data parsing and extraction 2.8 10.0
Domain specific 3.0 10.0
General Intelligence 5.1 3.4
Instructions following 6.6 10.0
Puzzle Solving 3.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models