Ling 3.0 Flash vs Ling 3.1 Flash
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
Ling 3.0 Flash23.7
Ling 3.1 Flash39.4
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty
Ling 3.0 Flash-17.9
Ling 3.1 Flash2.2
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps
Ling 3.0 Flash1.7
Ling 3.1 Flash18
AA Intelligence Index 4.3.2 AA Intelligence Index 4.3.2: Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score
Ling 3.0 Flash20.1
Ling 3.1 Flash41.1
AA Omniscience · Accuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test
Ling 3.0 Flash18.2
Ling 3.1 Flash29.1
AA Omniscience · Hallucination Rate AA Omniscience · Hallucination Rate: Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test · lower is better
Ling 3.0 Flash44.1
Ling 3.1 Flash37.9
AA-LCR (long context) 1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens)
Ling 3.0 Flash73
Ling 3.1 Flash83
GDP.pdf · AA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes
Ling 3.0 Flash5.4
Ling 3.1 Flash10
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench
Ling 3.0 Flash79.7
Ling 3.1 Flash—
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters
Ling 3.0 Flash32.3
Ling 3.1 Flash—
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts
Ling 3.0 Flash80.9
Ling 3.1 Flash—
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass
Ling 3.0 Flash0
Ling 3.1 Flash—
| Benchmark | Ling 3.0 Flash | Ling 3.1 Flash |
|---|---|---|
| Humanity's Last Exam | 23.7 | 39.4 |
| AA Omniscience Index | -17.9 | 2.2 |
| CritPt (physics) | 1.7 | 18 |
| AA Intelligence Index 4.3.2 | 20.1 | 41.1 |
| AA Omniscience · Accuracy | 18.2 | 29.1 |
| AA Omniscience · Hallucination Rate | 44.1 | 37.9 |
| AA-LCR (long context) 1.1 | 73 | 83 |
| GDP.pdf · AA all-pass | 5.4 | 10 |
| Vals LegalBench | 79.7 | — |
| Vals MedCode | 32.3 | — |
| Vals MedScribe | 80.9 | — |
| Vals Legal Research Bench | 0 | — |
Specs
| Spec | Ling 3.0 Flash | Ling 3.1 Flash |
|---|---|---|
| Input, per 1M | $0.06 | $0.30 |
| Output, per 1M | $0.18 | $0.90 |
| Cost per task? | — | $1.00 |
| Speed, tok/s | 182 | 145 |
| Context | 262K | 1M |
| Weights | Open | Open |
| Released | Aug 2026 | Oct 2026 |
| Memory (4-bit) | 76 GB | 343 GB |
| Licence | MIT | MIT |
| Commercial use | Allowed | Allowed |
| See images | — | — |
| Read PDFs | — | — |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | Partial | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
Ling 3.0 Flash → Ling 3.1 Flash
Memory (4-bit): 76 GB → 343 GB
Ling 3.1 Flash → Ling 3.0 Flash