Claude Sonnet 4.5 vs Gemini 2.5 Flash
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.Gemini 2.5 Flash is cheaper.
Scores updated · 36 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 thinking40Claude Sonnet 4.54 of 5 tests · 1 tie
- CodingWriting and fixing software30Claude Sonnet 4.53 of 3 tests
- FactsGetting facts right instead of making them up21Claude Sonnet 4.52 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Claude Sonnet 4.51 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Sonnet 4.51 of 1 test
- Images and chartsUnderstanding pictures, charts and video00Even0 each · 2 ties
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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Sonnet 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+26.2points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+22points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+16.8points ahead
Where Gemini 2.5 Flash pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- Terminal-Bench HardClaude Sonnet 4.5 by 2235.613.6+22
- SWE-bench VerifiedClaude Sonnet 4.5 by 16.877.260.4+16.8
- SciCodeClaude Sonnet 4.5 by 16.645.729.1+16.6
ReasoningClaude Sonnet 4.5
- SimpleBenchClaude Sonnet 4.5 by 13.154.341.2+13.1
- ARC-AGI-2Claude Sonnet 4.5 by 11.113.62.5+11.1
- Humanity's Last ExamClaude Sonnet 4.5 by 5.717.812.1+5.7
- GPQA DiamondClaude Sonnet 4.5 by 4.483.479+4.4
- CritPttie1.11.1tie
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 26.250.924.7+26.2
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 6.932.925.9+6.9
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Flash by 4.2127.8+4.2
Following instructionsClaude Sonnet 4.5
- IFBenchClaude Sonnet 4.5 by 757.350.3+7
Other results20 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.
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 46.578.131.6+46.5
- ARC-AGI-1Claude Sonnet 4.5 by 31.463.732.3+31.4
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 29.952.122.2+29.9
- AA-OmniscienceClaude Sonnet 4.5 by 29.7-0.1-29.8+29.7
- HarmBenchClaude Sonnet 4.5 by 29.49262.6+29.4
- MRCRClaude Sonnet 4.5 by 23.455.432+23.4
- AIR-Bench 2024Claude Sonnet 4.5 by 21.189.868.7+21.1
- AIME 2025Claude Sonnet 4.5 by 158772+15
- AA IntelligenceClaude Sonnet 4.5 by 7.620.713.1+7.6
- LiveCodeBenchGemini 2.5 Flash by 5.27176.2+5.2
- vectara_factual_consistencyGemini 2.5 Flash by 4.28892.2+4.2
- vectara_answer_rateGemini 2.5 Flash by 3.495.699+3.4
- HMMT Feb. 2025Claude Sonnet 4.5 by 3.367.564.2+3.3
- vectara_avg_summary_lengthClaude Sonnet 4.5 by 26.3 rating points127.8101.5+26.3 rating
- XSTestGemini 2.5 Flash by 2.496.498.8+2.4
- simple_safety_testsClaude Sonnet 4.5 by 210098+2
- AA Agentic IndexGemini 2.5 Flash by 1.317.518.8+1.3
- bbqClaude Sonnet 4.5 by 1.298.997.7+1.2
- anthropic_red_teamtie98.298.8tie
- frontiermath_tier_4_v1tie4.24.2tie
Questions people ask
Which is better, Claude Sonnet 4.5 or Gemini 2.5 Flash?
Claude Sonnet 4.5 wins six of the seven areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Gemini 2.5 Flash wins none, but costs 84% less. They are level on images and charts.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 3 coding tests both models report; Gemini 2.5 Flash wins none.
Which is cheaper?
Claude Sonnet 4.5 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 36 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 20 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.