ling-3.0-flash-2607: benchmark results
Provider: InclusionAI.
Aggregate Rating 1679 ± 41, rank #455 of 10916 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI LiveCodeBench | 83.99 | Accuracy (%) | 69.7 |
| Vals AI GPQA | 84.85 | Accuracy (%) | 64.1 |
| Vals AI CorpFin v2 | 61.93 | Accuracy (%) | 62.6 |
| Vals AI MedScribe | 80.9 | Accuracy (%) | 50 |
| Vals AI MMLU-Pro | 82.01 | Accuracy (%) | 41.3 |
| Vals AI TaxEval v2 | 70.65 | Accuracy (%) | 39.2 |
| Vals AI LegalBench | 79.69 | Accuracy (%) | 37 |
| Vals AI Harvey Legal Agent Bench | 1.25 | Accuracy (%) | 29.4 |
| Vals AI Terminal-Bench 2.1 | 50.19 | Accuracy (%) | 20.7 |
| Vals AI SWE-bench Verified | 65.2 | Resolved (%) | 17.2 |
| Vals AI MedCode | 32.28 | Accuracy (%) | 15.9 |
| Vals AI Finance Agent v2 | 30.31 | Accuracy (%) | 9.9 |
Interactive version: theaggregate.ai/model?slug=ling-3-0-flash-2607 · How It Works · Data refreshed daily, snapshot 2026-11-08.