Harvey LAB-AA v1.1 ↗0.00%
Gemini 3.5 Flash-Lite · Harvey LAB-AA v1.1 · all-pass ↗
Google / MODEL EVIDENCE
Gemini 3.5 Flash-Lite
40 benchmarks · 55 observations · 42 sources · released 2026-07-21
Scores at a glance
40 benchmarks · large dot: Gemini 3.5 Flash-Lite; small dots: closest models where reported
EnterpriseOps-Gym-AA ↗42.35%
Gemini 3.5 Flash-Lite · EnterpriseOps-Gym-AA ↗
GPQA Diamond ↗83.84 %
Gemini 3.5 Flash Lite · GPQA Diamond · Accuracy ↗
3 more reported results
83.33% · Gemini 3.5 Flash-Lite · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗
75.76% · Gemini 3.5 Flash-Lite · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗
74.24% · Gemini 3.5 Flash-Lite · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗
Gemini 3.5 Flash-Lite · FrontierMath-Tiers-1-3-v2-Private · Best score (across scorers) · % ↗
Gemini 3.5 Flash-Lite · FrontierMath-Tier-4-v2-Private · Best score (across scorers) · % ↗
Gemini 3.5 Flash-Lite · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
2 more reported results
60% · Gemini 3.5 Flash-Lite · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗
51.11% · Gemini 3.5 Flash-Lite · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗
Gemini 3.5 Flash-Lite · Chess Puzzles · Best score (across scorers) · % ↗
2 more reported results
16% · Gemini 3.5 Flash-Lite · Chess Puzzles · Best score (across scorers) · % · Epoch AI · Chess Puzzles ↗
7% · Gemini 3.5 Flash-Lite · Chess Puzzles · Best score (across scorers) · % · Epoch AI · Chess Puzzles ↗
Gemini 3.5 Flash-Lite · Mystery Game Puzzles · Best score (across scorers) · % ↗
1 more reported result
12% · Gemini 3.5 Flash-Lite · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗
ARC-AGI-1 ↗53.5%
Gemini 3.5 Flash-Lite · ARC-AGI · Score · % ↗
3 more reported results
32.33% · Gemini 3.5 Flash-Lite (medium) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗
17% · Gemini 3.5 Flash-Lite · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗
7.5% · Gemini 3.5 Flash-Lite · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗
Gemini 3.5 Flash-Lite · WeirdML · Accuracy · % ↗
Gemini 3.5 Flash-Lite · APEX-Agents · Pass@1 score · % ↗
ARC-AGI-2 ↗10.28%
Gemini 3.5 Flash-Lite · ARC-AGI-2 · Score · % ↗
3 more reported results
5.28% · Gemini 3.5 Flash-Lite (medium) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗
1.53% · Gemini 3.5 Flash-Lite · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗
0.83% · Gemini 3.5 Flash-Lite · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗
CritPt ↗0%
Gemini 3.5 Flash-Lite · CritPt · Accuracy · % ↗
ProofBench ↗13%
Gemini 3.5 Flash-Lite · ProofBench · Accuracy · % ↗
LMCA ↗37.6%
Gemini 3.5 Flash-Lite · LMCA · Score · % ↗
DTBench ↗83.47%
Gemini 3.5 Flash-Lite · DTBench · Accuracy · % ↗
GDP.pdf ↗10%
Gemini 3.5 Flash-Lite · GDP.pdf · GDP.pdf score · % ↗
SciCode ↗41.32%
Gemini 3.5 Flash-Lite · SciCode · Score · % ↗
Text Arena (Coding) ↗1446.62 Elo
Gemini 3.5 Flash-Lite · WebDev Arena · Elo ↗
Epoch Capabilities Index (ECI) ↗144.91 ECI
Gemini 3.5 Flash-Lite · General ECI · 26 October 2026 fit ↗
Legal Research Bench ↗13.94 %
Gemini 3.5 Flash Lite · Legal Research Bench · All-Pass ↗
LegalBench ↗84.07 %
Gemini 3.5 Flash Lite · LegalBench · Accuracy ↗
Gemini 3.5 Flash Lite · Harvey's Legal Agent Benchmark v1 · Accuracy ↗
Tax Agent Bench ↗7.25 %
Gemini 3.5 Flash Lite · Tax Agent Bench · Accuracy ↗
Vals Finance Agent v2 ↗47.44 %
Gemini 3.5 Flash Lite · Finance Agent v2 · Accuracy ↗
Gemini 3.5 Flash Lite · Excel Modeling Benchmark v1 · Accuracy ↗
CorpFin v2 ↗60.68 %
Gemini 3.5 Flash Lite · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗68.68 %
Gemini 3.5 Flash Lite · MortgageTax · Accuracy ↗
1 more reported result
72.61 % · Gemini 3.5 Flash Lite · TaxEval · Accuracy · Vals AI · TaxEval ↗
MedCode ↗43.49 %
Gemini 3.5 Flash Lite · MedCode · Accuracy ↗
MedScribe ↗70.89 %
Gemini 3.5 Flash Lite · MedScribe · Accuracy ↗
MMLU-Pro ↗85.84 %
Gemini 3.5 Flash Lite · MMLU Pro · Accuracy ↗
MMMU-Pro ↗83.58 %
Gemini 3.5 Flash Lite · MMMU Pro · Accuracy ↗
Gemini 3.5 Flash Lite · SAGE · Accuracy ↗
Vibe Code Bench ↗37.16 %
Gemini 3.5 Flash Lite (OpenHands) · Vibe Code Bench · original task set ↗
Gemini 3.5 Flash Lite · ProgramBench · Accuracy ↗
Code Migration v1.1 ↗6.15 %
Gemini 3.5 Flash Lite · Code Migration v1 · Accuracy ↗
Gemini 3.5 Flash Lite (Mini-SWE-agent) · SWE-bench Verified · Score ↗
LiveCodeBench ↗79.01 %
Gemini 3.5 Flash Lite · LiveCodeBench · Accuracy ↗
CyberBench v1.1 ↗59.11 %
Gemini 3.5 Flash Lite · CyberBench · Accuracy ↗
Public Benefits Bench v1.1 ↗51.83 %
Gemini 3.5 Flash Lite · Public Benefits Bench · Accuracy ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
17 of 25 shared benchmark comparisons
Qwen 3.6 Plus →Qwen
17 of 25 shared benchmark comparisons
Gemini 3 Flash (12/25) →Google
17 of 25 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.
- ARC Prize - Leaderboard ↗
- Arena leaderboard — WebDev evaluation ↗
- EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗
- Harvey LAB-AA v1.1 Benchmark | Artificial Analysis ↗
- SciCode Benchmark | Artificial Analysis ↗
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- APEX-Agents ↗
- ARC-AGI-2 ↗
- Chess Puzzles ↗
- CritPt v1 ↗
- FrontierMath Tier 4 (v2) ↗
- FrontierMath Tiers 1-3 (v2) ↗
- GPQA Diamond ↗
- Mystery Game Puzzles ↗
- OTIS Mock AIME 2024-2025 ↗
- AI benchmarks & capabilities ↗
- WeirdML ↗
- GDP.pdf Benchmark | Surge AI ↗
- Code Migration v1 — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- CyberBench — 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 ↗
- ProofBench — evaluation methodology and results ↗
- Public Benefits Bench — 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 ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
Gemini 3.5 Flash Lite · Gemini 3.5 Flash Lite (Mini-SWE-agent) · Gemini 3.5 Flash Lite (OpenHands) · Gemini 3.5 Flash-Lite · Gemini 3.5 Flash-Lite (medium)