Ling 3.0 Flash VL
InclusionAI · released Sep 10, 2026
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...
Specification
- Context window
- 131K
- Max output
- 33K
- Knowledge cutoff
- Not stated
- Parameters
- 124.8B
- Licence
- mit
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
24.6
75th percentile
Coding
57.0
Coding Index
Agentic
28.7
Agentic Index
Output speed
34 t/s
Median across providers
Latency
1.9s
Time to first token
Cost per task
$0.02
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond86.2%
- AA-LCR (long context)78.3%
- SciCode44.2%
- τ²-bench (Telecom)34.4%
- Humanity's Last Exam22.0%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 86.2% |
| AA-LCR (long context) | 78.3% |
| SciCode | 44.2% |
| τ²-bench (Telecom) | 34.4% |
| Humanity's Last Exam | 22.0% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- InklingThinking Machines25.0
- Inkling (free)Thinking Machines25.0
- Grok 4.3xAI24.9
- Claude Sonnet 4.6Anthropic24.7
- GPT-5.1OpenAI24.7
- Ling 3.0 Flash VLInclusionAI24.6
- Qwen3 MaxQwen24.5
- Ling 3.0 Tiny (free)InclusionAI24.3
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Inkling | 25.0 |
| Inkling (free) | 25.0 |
| Grok 4.3 | 24.9 |
| Claude Sonnet 4.6 | 24.7 |
| GPT-5.1 | 24.7 |
| Ling 3.0 Flash VL | 24.6 |
| Qwen3 Max | 24.5 |
| Ling 3.0 Tiny (free) | 24.3 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.06
- Output / 1M tokens
- $0.18
- Cached input / 1M
- $0.012
- Blended 3:1
- $0.09
One task, estimated
$0.02
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.