Vals Multimodal Index ↗41.35 %
Gemini 3.1 Flash Lite Preview · Vals Multimodal Index · Accuracy ↗
Google / MODEL EVIDENCE
Gemini 3.1 Flash Lite Preview
27 benchmarks · 28 observations · 28 sources
Scores at a glance
27 benchmarks · large dot: Gemini 3.1 Flash Lite Preview; small dots: closest models where reported
Legal Research Bench ↗3.37 %
Gemini 3.1 Flash Lite Preview · Legal Research Bench · All-Pass ↗
LegalBench ↗83.76 %
Gemini 3.1 Flash Lite Preview · LegalBench · Accuracy ↗
Gemini 3.1 Flash Lite Preview · Harvey's Legal Agent Benchmark v1 · Accuracy ↗
CaseLaw v2 ↗54.98 %
Gemini 3.1 Flash Lite Preview · CaseLaw · Accuracy ↗
Tax Agent Bench ↗3.11 %
Gemini 3.1 Flash Lite Preview · Tax Agent Bench · Accuracy ↗
Vals Finance Agent v2 ↗29.99 %
Gemini 3.1 Flash Lite Preview · Finance Agent v2 · Accuracy ↗
Gemini 3.1 Flash Lite Preview · Excel Modeling Benchmark v1 · Accuracy ↗
CorpFin v2 ↗59.36 %
Gemini 3.1 Flash Lite Preview · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗68.04 %
Gemini 3.1 Flash Lite Preview · MortgageTax · Accuracy ↗
1 more reported result
71.79 % · Gemini 3.1 Flash Lite Preview · TaxEval · Accuracy · Vals AI · TaxEval ↗
MedCode ↗47.6 %
Gemini 3.1 Flash Lite Preview · MedCode · Accuracy ↗
MedScribe ↗63.9 %
Gemini 3.1 Flash Lite Preview · MedScribe · Accuracy ↗
AIME 2024–2025 · Vals ↗83.33 %
Gemini 3.1 Flash Lite Preview · AIME · Accuracy ↗
GPQA Diamond ↗81.06 %
Gemini 3.1 Flash Lite Preview · GPQA Diamond · Accuracy ↗
MMLU-Pro ↗86.24 %
Gemini 3.1 Flash Lite Preview · MMLU Pro · Accuracy ↗
MMMU-Pro ↗82.49 %
Gemini 3.1 Flash Lite Preview · MMMU Pro · Accuracy ↗
Gemini 3.1 Flash Lite Preview · SAGE · Accuracy ↗
Gemini 3.1 Flash Lite Preview (OpenHands) · Vibe Code Bench · original task set ↗
Gemini 3.1 Flash Lite Preview · ProgramBench · Accuracy ↗
Code Migration v1.1 ↗4.61 %
Gemini 3.1 Flash Lite Preview · Code Migration v1 · Accuracy ↗
SWE-bench Verified ↗62.8 %
Gemini 3.1 Flash Lite Preview (Mini-SWE-agent) · SWE-bench Verified · Score ↗
LiveCodeBench ↗80.12 %
Gemini 3.1 Flash Lite Preview · LiveCodeBench · Accuracy ↗
gemini-3.1-flash-lite-preview · Scale Labs · large ↗
Fortress ↗51.05%
gemini-3.1-flash-lite-preview · Scale Labs · Risk elicitation score ↗
gemini-3.1-flash-lite-preview · Scale Labs · Score ↗
TutorBench ↗51.50%
gemini-3.1-flash-lite-preview · Scale Labs · Score ↗
VISTA ↗46.93%
gemini-3.1-flash-lite-preview · Scale Labs · Score ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Gemini 3.5 Flash Lite →Google
17 of 27 shared benchmark comparisons
GPT-5.4 Mini →OpenAI
17 of 27 shared benchmark comparisons
Gemini 3 Flash (12/25) →Google
20 of 27 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.
- Scale Labs — evaluation methodology and results ↗
- Scale Labs — evaluation methodology and results ↗
- Scale Labs — evaluation methodology and results ↗
- Scale Labs — evaluation methodology and results ↗
- Scale Labs — evaluation methodology and results ↗
- AIME — evaluation methodology and results ↗
- CaseLaw — evaluation methodology and results ↗
- Code Migration v1 — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- Excel Modeling Benchmark v1 — evaluation methodology and results ↗
- Finance Agent v2 — evaluation methodology and results ↗
- GPQA Diamond — evaluation methodology and results ↗
- Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗
- LiveCodeBench — 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 ↗
- MMLU Pro — evaluation methodology and results ↗
- MMMU Pro — evaluation methodology and results ↗
- MortgageTax — evaluation methodology and results ↗
- ProgramBench — evaluation methodology and results ↗
- SAGE — evaluation methodology and results ↗
- SWE-bench Verified — evaluation methodology and results ↗
- Tax Agent Bench — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
- Vals Multimodal Index — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
Gemini 3.1 Flash Lite Preview · Gemini 3.1 Flash Lite Preview (Mini-SWE-agent) · Gemini 3.1 Flash Lite Preview (OpenHands) · gemini-3.1-flash-lite-preview