Ant GroupLing 3.1 Flash
Ling 3.1 Flash is an Ant Group proprietary reasoning model, released 29 Sept 2026. It is not yet ranked: 4 independent results so far, and the index needs at least five across two categories. At $0.450 per million tokens blended it is cheaper than most ranked models. Output speed of 214 tokens per second puts it in the fastest quarter, with a first answer in 11.1 s.
- Blended price
- $0.450/M
- $0.300 in · $0.900 out
- Output speed
- 214 tok/s
- measured by Artificial Analysis
- First answer
- 11 s
- first token 2.51 s
- Context
- 262k
- Full answer
- 13 s
- median, reasoning included
- Cost per run
- $0.986
- one full Intelligence Index run
- Released
- 29 Sept 2026
- Reasoning71
- Knowledge63
- Long context67
- Composite76
Versions
Ant Group has shipped 3 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Ling 3.1 Flashthis page | 29 Sept 2026 | – | – |
| Ling 3.0 Flash | 23 Jul 2026 | 52.9 | #284 |
| Ling Flash 2.0 | 18 Sept 2025 | 44.6 | #510 |
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| Humanity's Last Exam (AA)not in index | 39.4%#85 | Artificial Analysis |
| CritPt | 18.0%#66 | Artificial Analysis |
Coding
| Benchmark | not stated | Source |
|---|---|---|
| SciCode (AA)not in index | 54.0%#64 | Artificial Analysis |
| Terminal-Bench 4.0 (AA)not in index | 33.3%#35 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| GDPval-AA v2.1not in index | 56.1%#22 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| AA-Omniscience | 2.2#114 | Artificial Analysis |
| AA-Omniscience: accuracynot in index | 29.1%#180 | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 62.1%#65 | Artificial Analysis |
Long context
| Benchmark | not stated | Source |
|---|---|---|
| AA-LCR | 83.0%#24 | Artificial Analysis |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| AA Intelligence Index v4.3.2 | 41.1#54 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| NovitaAI | 69 tok/s | 2.71 s | $0.000 | $0.000 | 262k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0004 | – | 12.5 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0041 | – | 13.9 s |
| Code edit | 6,000 / 1,500 | $0.0032 | – | 18.2 s |
| Agentic coding session | 60,000 / 4,000 | $0.022 | – | 29.9 s |
| Structured extraction | 2,000 / 200 | $0.0008 | – | 12.1 s |
See also
Data as of 11 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Ling 3.1 Flash: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/ling-3-1-flash, data as of 11 Oct 2026.