Claude Sonnet 4.6 vs Gemini 3.1 Flash Lite Preview
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 2 of 7 areas
Images and charts · Following instructions
Claude Sonnet 4.6 is the stronger all-rounder.Gemini 3.1 Flash Lite Preview is cheaper and better at images and charts.
Scores updated · 31 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software40Claude Sonnet 4.64 of 4 tests
- AgentsCarrying out multi-step tasks on its own40Claude Sonnet 4.64 of 4 tests
- ReasoningHard problems that need careful thinking30Claude Sonnet 4.63 of 3 tests
- FactsGetting facts right instead of making them up21Claude Sonnet 4.62 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.61 of 1 test
- Images and chartsUnderstanding pictures, charts and video12Gemini 3.1 Flash Lite Preview2 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemini 3.1 Flash Lite Preview1 of 1 test
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 3.1 Flash Lite Preview costs 90% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Sonnet 4.6 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+40.1points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+28.8points ahead
Where Gemini 3.1 Flash Lite Preview pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+20.6points ahead
- Harder college exam questions with imagesMMMU-Pro+2.2points ahead
- Reasoning about charts from research papersCharXiv (RQ)+1.6points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.6
- Terminal-Bench 2.1Claude Sonnet 4.6 by 40.171.231.1+40.1
- Terminal-Bench HardClaude Sonnet 4.6 by 28.85324.2+28.8
- LMArena · WebDevClaude Sonnet 4.6 by 267 rating points15211254+267 rating
- SciCodeClaude Sonnet 4.6 by 6.750.143.4+6.7
AgentsClaude Sonnet 4.6
- GDPValClaude Sonnet 4.6 by 36.736.70+36.7
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 24.734.49.7+24.7
- AA ApexAgentsClaude Sonnet 4.6 by 15.82812.2+15.8
- Terminal-Bench 4.0Claude Sonnet 4.6 by 2.530.5+2.5
ReasoningClaude Sonnet 4.6
- Humanity's Last ExamClaude Sonnet 4.6 by 16.433.617.2+16.4
- GPQA DiamondClaude Sonnet 4.6 by 5.387.582.2+5.3
- CritPtClaude Sonnet 4.6 by 23.11.1+2
FactsClaude Sonnet 4.6
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 34.351.617.3+34.3
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 4.640.936.3+4.6
- Vectara HHEM hallucination ratelower is betterGemini 3.1 Flash Lite Preview by 2.410.68.2+2.4
Images and chartsGemini 3.1 Flash Lite Preview
- LMArena · VisionClaude Sonnet 4.6 by 43 rating points12831240+43 rating
- MMMU-ProGemini 3.1 Flash Lite Preview by 2.273.375.5+2.2
- CharXiv (RQ)Gemini 3.1 Flash Lite Preview by 1.671.673.2+1.6
Following instructionsGemini 3.1 Flash Lite Preview
- IFBenchGemini 3.1 Flash Lite Preview by 20.656.677.2+20.6
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.
- GDPval-AA v2Claude Sonnet 4.6 by 753 rating points1395642+753 rating
- τ²-Bench Telecom (AA run)Claude Sonnet 4.6 by 44.475.731.3+44.4
- AA Agentic IndexClaude Sonnet 4.6 by 29.933.13.2+29.9
- AA-OmniscienceClaude Sonnet 4.6 by 28.612.2-16.4+28.6
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 28.36334.7+28.3
- Finance Agent v2Claude Sonnet 4.6 by 215130+21
- AA IntelligenceClaude Sonnet 4.6 by 14.530.115.6+14.5
- Legal Agent BenchmarkClaude Sonnet 4.6 by 5.45.40+5.4
- vectara_avg_summary_lengthClaude Sonnet 4.6 by 52.1 rating points114.762.6+52.1 rating
- vectara_factual_consistencyGemini 3.1 Flash Lite Preview by 2.489.491.8+2.4
- MMMLUtie89.388.9tie
- vectara_answer_ratetie99.999.6tie
Questions people ask
Which is better, Claude Sonnet 4.6 or Gemini 3.1 Flash Lite Preview?
Claude Sonnet 4.6 wins five of the seven areas where both have results: coding, agents, reasoning, facts and long documents. Gemini 3.1 Flash Lite Preview wins images and charts and following instructions, and costs 90% less.
Which is better for coding?
Claude Sonnet 4.6. It wins 4 of the 4 coding tests both models report; Gemini 3.1 Flash Lite Preview wins none.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 3.1 Flash Lite Preview costs $0.25 and $1.50. That makes Gemini 3.1 Flash Lite Preview about 90% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 19 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.