Gemini 3.5 Flash Lite vs Inkling
Wins 0 of 8 areas
—
Wins 6 of 8 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Inkling is the stronger all-rounder.Gemini 3.5 Flash Lite is cheaper.
Scores updated · 37 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking05Inkling5 of 5 tests
- MathCompetition and research-level math05Inkling5 of 5 tests
- CodingWriting and fixing software24Inkling4 of 6 tests
- AgentsCarrying out multi-step tasks on its own02Inkling2 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts01Inkling1 of 1 test
- Following instructionsDoing exactly what it is asked01Inkling1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
- Images and chartsUnderstanding pictures, charts and video11Even1 each
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Gemini 3.5 Flash Lite costs 45% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Inkling pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+26.2points ahead
- Harvard-MIT high-school math contest problemsHMMT Feb. 2026+22.7points ahead
- Fresh logic puzzles that change regularlyLiveBench · Reasoning+18.2points ahead
Where Gemini 3.5 Flash Lite pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33.3points ahead
- Harder college exam questions with imagesMMMU-Pro+5.5points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+5.1points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingInkling
- SciCodeInkling by 5.741.347+5.7
- LiveBench · CodingGemini 3.5 Flash Lite by 5.176.171+5.1
- LiveBench · Agentic CodingInkling by 4.145.349.4+4.1
- LMArena · WebDevGemini 3.5 Flash Lite by 28 rating points14401412+28 rating
- SWE-bench VerifiedInkling by 2.67577.6+2.6
- Terminal-Bench 2.1Inkling by 1.553.655.1+1.5
AgentsInkling
- τ-Bench V3 · BankingInkling by 11.617.529.1+11.6
- GDPValInkling by 4.524.328.8+4.5
- Terminal-Bench 4.0tie11tie
ReasoningInkling
- ARC-AGI-2Inkling by 26.210.336.5+26.2
- LiveBench · ReasoningInkling by 18.260.278.3+18.2
- Humanity's Last ExamInkling by 13.118.831.9+13.1
- CritPtInkling by 5.405.4+5.4
- GPQA DiamondInkling by 3.483.887.2+3.4
FactsEven
- AA-Omniscience · Non-hallucinationGemini 3.5 Flash Lite by 33.365.632.3+33.3
- AA-Omniscience · AccuracyInkling by 12.129.541.5+12.1
Images and chartsEven
- MMMU-ProGemini 3.5 Flash Lite by 5.57973.5+5.5
- CharXiv (RQ)Inkling by 1.676.578.1+1.6
MathInkling
- HMMT Feb. 2026Inkling by 22.763.686.3+22.7
- AIME 2026Inkling by 14.982.297.1+14.9
- LiveBench · MathematicsInkling by 14.773.788.4+14.7
- FrontierMath Tiers 1-3 (v2)Inkling by 7.32633.3+7.3
- FrontierMath Tier 4Inkling by 4.904.9+4.9
Following instructionsInkling
- LiveBench · Instruction FollowingInkling by 2.967.270.1+2.9
Other results12 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- ARC-AGI-1Inkling by 2653.579.5+26
- livebench_data_analysisInkling by 19.553.372.8+19.5
- Toolathlon VerifiedGemini 3.5 Flash Lite by 11.657.145.5+11.6
- GDPval-AA v2Inkling by 98 rating points11401238+98 rating
- AA Agentic IndexInkling by 8.415.924.3+8.4
- τ³-Bench BankingInkling by 7.216.523.7+7.2
- HLE (with tools)Inkling by 4.142.546.6+4.1
- AA-OmniscienceGemini 3.5 Flash Lite by 3.25.22+3.2
- AA IntelligenceInkling by 2.822.225+2.8
- Artificial Analysis Coding IndexInkling by 2.849.352.1+2.8
- livebench_languageInkling by 1.771.873.5+1.7
- SWEBench Pro PublicGemini 3.5 Flash Lite by 154.253.2+1
Questions people ask
Which is better, Gemini 3.5 Flash Lite or Inkling?
Inkling wins six of the eight areas we test: coding, agents, reasoning, math, long documents and following instructions. Gemini 3.5 Flash Lite wins none, but costs 45% less. They are level on facts and images and charts.
Which is better for coding?
Inkling. It wins 4 of the 6 coding tests both models report; Gemini 3.5 Flash Lite wins 2.
Which is cheaper?
Gemini 3.5 Flash Lite costs $0.30 per million input tokens and $2.50 per million output tokens; Inkling costs $1.00 and $4.05. That makes Gemini 3.5 Flash Lite about 45% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 25 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.