Claude Sonnet 4 vs Gemini 2.5 Flash
Wins 3 of 7 areas
Coding · Long documents · Following instructions
Wins 2 of 7 areas
Facts · Images and charts
Claude Sonnet 4 wins more areas, narrowly.Gemini 2.5 Flash is cheaper and better at images and charts.
Scores updated · 41 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 software30Claude Sonnet 43 of 3 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 video03Gemini 2.5 Flash3 of 3 tests
- FactsGetting facts right instead of making them up12Gemini 2.5 Flash2 of 3 tests
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking22Even2 each · 1 tie
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 costs 84% 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 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+46.2points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+17.5points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+12.3points ahead
Where Gemini 2.5 Flash pulls ahead
- Harder college exam questions with imagesMMMU-Pro+7.3points ahead
- College exam questions with charts, maps and diagramsMMMU+5.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.3points ahead
Every test, side by side
All 41 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 17.531.113.6+17.5
- SWE-bench VerifiedClaude Sonnet 4 by 12.372.760.4+12.3
- SciCodeClaude Sonnet 4 by 10.94029.1+10.9
ReasoningEven
- SimpleBenchClaude Sonnet 4 by 4.345.541.2+4.3
- ARC-AGI-2Claude Sonnet 4 by 3.45.92.5+3.4
- Humanity's Last ExamGemini 2.5 Flash by 1.410.712.1+1.4
- GPQA DiamondGemini 2.5 Flash by 1.377.779+1.3
- CritPttie0.31.1tie
FactsGemini 2.5 Flash
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 46.270.924.7+46.2
- AA-Omniscience · AccuracyGemini 2.5 Flash by 3.322.725.9+3.3
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Flash by 2.510.37.8+2.5
Images and chartsGemini 2.5 Flash
- MMMU-ProGemini 2.5 Flash by 7.361.869.1+7.3
- MMMUGemini 2.5 Flash by 5.374.479.7+5.3
- LMArena · VisionGemini 2.5 Flash by 44 rating points11911235+44 rating
Following instructionsClaude Sonnet 4
- IFBenchClaude Sonnet 4 by 4.454.750.3+4.4
Other results24 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.
- AIME 2024Gemini 2.5 Flash by 38.943.482.3+38.9
- HarmBenchClaude Sonnet 4 by 35.49862.6+35.4
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 3364.631.6+33
- AA-OmniscienceClaude Sonnet 4 by 300.2-29.8+30
- AIR-Bench 2024Claude Sonnet 4 by 19.688.368.7+19.6
- livecodebench_hardGemini 2.5 Flash by 15.732.648.3+15.7
- Artificial Analysis Coding IndexClaude Sonnet 4 by 15.437.622.2+15.4
- SimpleQAGemini 2.5 Flash by 1115.926.9+11
- Aider-PolyglotClaude Sonnet 4 by 8.870.761.9+8.8
- ARC-AGI-1Claude Sonnet 4 by 7.74032.3+7.7
- LiveCodeBenchGemini 2.5 Flash by 7.768.576.2+7.7
- livecodebench_mediumGemini 2.5 Flash by 6.57682.5+6.5
- AA IntelligenceClaude Sonnet 4 by 5.818.913.1+5.8
- vectara_avg_summary_lengthClaude Sonnet 4 by 44.3 rating points145.8101.5+44.3 rating
- frontiermath_tier_4_v1Gemini 2.5 Flash by 4.204.2+4.2
- vectara_factual_consistencyGemini 2.5 Flash by 2.589.792.2+2.5
- XSTestGemini 2.5 Flash by 2.296.698.8+2.2
- simple_safety_testsClaude Sonnet 4 by 210098+2
- AIME 2025Gemini 2.5 Flash by 1.570.572+1.5
- AA Agentic IndexGemini 2.5 Flash by 1.217.618.8+1.2
- bbqGemini 2.5 Flash by 1.196.697.7+1.1
- anthropic_red_teamtie99.298.8tie
- vectara_answer_ratetie98.699tie
- livecodebench_easytie98.899.1tie
Questions people ask
Which is better, Claude Sonnet 4 or Gemini 2.5 Flash?
Claude Sonnet 4 wins three of the seven areas where both have results: coding, long documents and following instructions. Gemini 2.5 Flash wins facts and images and charts, and costs 84% less. They are level on agents and reasoning.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 3 coding tests both models report; Gemini 2.5 Flash 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 costs $0.30 and $2.50. That makes Gemini 2.5 Flash about 84% cheaper for the same work.
How do you compare the two?
We use the 41 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 24 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.