Ant GroupLing 3.0 Tiny
Ling 3.0 Tiny is an Ant Group open-weights reasoning model, released 6 Aug 2026. Its best configuration ranks #419 of 785 on the BenchLeader Index at 48.7 ±4.9, in the lower half. The ± is the point: 330 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (55) and lowest in reasoning (41). Output speed of 57 tokens per second puts it slower than most, with a first answer in 37.8 s. Last measured 6 Aug 2026.
- Blended price
- –
- Output speed
- 57 tok/s
- measured by Artificial Analysis
- First answer
- 38 s
- Context
- 262k
- Full answer
- 47 s
- median, reasoning included
- Cost per run
- –
- Released
- 6 Aug 2026
- Overall index49
- Reasoning41
- Agents & tools49
- Knowledge53
- Long context55
- Composite42
How its index has moved
19 Sept 2026 to 18 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. 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 | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 73.4%#267 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 9.3%#337 | Artificial Analysis | |
| CritPt | 0.0%#315 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode (AA)not in index | 24.2%#221 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 27.7%#161 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GDPval-AA v2.1not in index | 3.0%#119 | Artificial Analysis | |
| τ³-Banking (AA) | 20.8%#94 | Artificial Analysis | |
| AutomationBenchnot in index | 0.3%#214 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 0.8%#210 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -19.4#242 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 8.5%#513 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 69.5%#46 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 60.3%#279 | Artificial Analysis | |
| MLCRnot in index | 10.0%#113 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 11.1#365 | Artificial Analysis |
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 | – | – | 43.1 s |
| Summarize a 30-page report | 12,000 / 600 | – | – | 48.4 s |
| Code edit | 6,000 / 1,500 | – | – | 1.1 min |
| Agentic coding session | 60,000 / 4,000 | – | – | 1.8 min |
| Structured extraction | 2,000 / 200 | – | – | 41.3 s |
See also
Questions people ask
- What are Ling 3.0 Tiny's benchmark scores?
- As of 24 Oct 2026, Ling 3.0 Tiny scores 48.7 ±4.9 on the BenchLeader Index, strongest in long context (55) and weakest in reasoning (41). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
- How does Ling 3.0 Tiny rank?
- Ling 3.0 Tiny is #419 of 785 ranked configurations on 24 Oct 2026. 330 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Ling 3.0 Tiny released?
- Ant Group released Ling 3.0 Tiny on 6 Aug 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Ling 3.0 Tiny: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/ling-3-0-tiny.