APEX-Agents-AA ↗27.43%
Ling-3.0-flash-Fin · APEX-Agents-AA ↗
InclusionAI / MODEL EVIDENCE
Ling-3.0-flash-Fin
13 benchmarks · 13 observations · 13 sources · released 2026-09-11
Scores at a glance
13 benchmarks · large dot: Ling-3.0-flash-Fin; small dots: closest models where reported
τ³-Banking ↗38.56%
Ling-3.0-flash-Fin · τ³-Banking ↗
Legal Research Bench ↗15.38 %
Ling 3.0 Flash Fin · Legal Research Bench · All-Pass ↗
LegalBench ↗68.74 %
Ling 3.0 Flash Fin · LegalBench · Accuracy ↗
Ling 3.0 Flash Fin · Harvey's Legal Agent Benchmark v1 · Accuracy ↗
Tax Agent Bench ↗20.6 %
Ling 3.0 Flash Fin · Tax Agent Bench · Accuracy ↗
Vals Finance Agent v2 ↗54.93 %
Ling 3.0 Flash Fin · Finance Agent v2 · Accuracy ↗
Ling 3.0 Flash Fin · Excel Modeling Benchmark v1 · Accuracy ↗
MedCode ↗29.3 %
Ling 3.0 Flash Fin · MedCode · Accuracy ↗
MedScribe ↗75.59 %
Ling 3.0 Flash Fin · MedScribe · Accuracy ↗
Vibe Code Bench ↗3.4 %
Ling 3.0 Flash Fin (OpenHands) · Vibe Code Bench · original task set ↗
Code Migration v1.1 ↗1.82 %
Ling 3.0 Flash Fin · Code Migration v1 · Accuracy ↗
CyberBench v1.1 ↗58.33 %
Ling 3.0 Flash Fin · CyberBench · Accuracy ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
9 of 13 shared benchmark comparisons
Gemini 3.5 Flash Lite →Google
10 of 13 shared benchmark comparisons
GPT-5.4 Nano →OpenAI
9 of 13 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- APEX-Agents-AA Benchmark | Artificial Analysis ↗
- 𝜏³-Banking Benchmark | Artificial Analysis ↗
- Code Migration v1 — evaluation methodology and results ↗
- CyberBench — evaluation methodology and results ↗
- Excel Modeling Benchmark v1 — evaluation methodology and results ↗
- Finance Agent v2 — evaluation methodology and results ↗
- Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗
- LegalBench — evaluation methodology and results ↗
- Legal Research Bench — evaluation methodology and results ↗
- MedCode — evaluation methodology and results ↗
- MedScribe — evaluation methodology and results ↗
- Tax Agent Bench — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
Ling 3.0 Flash Fin · Ling 3.0 Flash Fin (OpenHands) · Ling-3.0-flash-Fin