Claude Sonnet 4 vs Gemini 2.5 Flash Lite Preview 09-2025
Wins 5 of 7 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 2 of 7 areas
Agents · Images and charts
Claude Sonnet 4 is the stronger all-rounder.Gemini 2.5 Flash Lite Preview 09-2025 is cheaper and better at images and charts.
Scores updated · 17 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.
- ReasoningHard problems that need careful thinking20Claude Sonnet 42 of 3 tests · 1 tie
- CodingWriting and fixing software20Claude Sonnet 42 of 2 tests
- FactsGetting facts right instead of making them up20Claude Sonnet 42 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Sonnet 41 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Gemini 2.5 Flash Lite Preview 09-20251 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01Gemini 2.5 Flash Lite Preview 09-20251 of 1 test
Agents, 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 2.5 Flash Lite Preview 09-2025 costs 97% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+58.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+18.2points ahead
- Code for real scientific research problemsSciCode+11.3points ahead
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- Terminal-Bench HardClaude Sonnet 4 by 18.231.112.9+18.2
- SciCodeClaude Sonnet 4 by 11.34028.7+11.3
AgentsGemini 2.5 Flash Lite Preview 09-2025
- GDPValGemini 2.5 Flash Lite Preview 09-2025 by 7.99.717.6+7.9
ReasoningClaude Sonnet 4
- GPQA DiamondClaude Sonnet 4 by 6.877.770.9+6.8
- Humanity's Last ExamClaude Sonnet 4 by 3.710.77+3.7
- CritPttie0.30tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 58.770.912.2+58.7
- AA-Omniscience · AccuracyClaude Sonnet 4 by 4.722.718+4.7
Images and chartsGemini 2.5 Flash Lite Preview 09-2025
- MMMU-ProGemini 2.5 Flash Lite Preview 09-2025 by 3.261.865+3.2
- LMArena · Visiontie11911198tie
Following instructionsClaude Sonnet 4
- IFBenchClaude Sonnet 4 by 2.154.752.6+2.1
Other results5 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.
- AA-OmniscienceClaude Sonnet 4 by 54.20.2-54+54.2
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 33.964.630.7+33.9
- Artificial Analysis Coding IndexClaude Sonnet 4 by 15.537.622.1+15.5
- AA IntelligenceClaude Sonnet 4 by 8.518.910.4+8.5
- AA Agentic IndexGemini 2.5 Flash Lite Preview 09-2025 by 5.417.623+5.4
Questions people ask
Which is better, Claude Sonnet 4 or Gemini 2.5 Flash Lite Preview 09-2025?
Claude Sonnet 4 wins five of the seven areas where both have results: coding, reasoning, facts, long documents and following instructions. Gemini 2.5 Flash Lite Preview 09-2025 wins agents and images and charts, and costs 97% less.
Which is better for coding?
Claude Sonnet 4. It wins 2 of the 2 coding tests both models report; Gemini 2.5 Flash Lite Preview 09-2025 wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 2.5 Flash Lite Preview 09-2025 costs $0.10 and $0.40. That makes Gemini 2.5 Flash Lite Preview 09-2025 about 97% cheaper for the same work.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.