Claude Sonnet 4.5 vs Gemini 2.5 Pro
Wins 6 of 8 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 2 of 8 areas
Facts · Images and charts
Claude Sonnet 4.5 is the stronger all-rounder.Gemini 2.5 Pro is cheaper and better at facts.
Scores updated · 62 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.
- CodingWriting and fixing software40Claude Sonnet 4.54 of 5 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own30Claude Sonnet 4.53 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts20Claude Sonnet 4.52 of 2 tests
- Following instructionsDoing exactly what it is asked20Claude Sonnet 4.52 of 2 tests
- ReasoningHard problems that need careful thinking21Claude Sonnet 4.52 of 5 tests · 2 ties
- MathCompetition and research-level math10Claude Sonnet 4.51 of 2 tests · 1 tie
- FactsGetting facts right instead of making them up13Gemini 2.5 Pro3 of 4 tests
- Images and chartsUnderstanding pictures, charts and video02Gemini 2.5 Pro2 of 3 tests · 1 tie
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 Pro costs 38% 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 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+41.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+27.3points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+14.8points ahead
Where Gemini 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+25.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.2points ahead
- Harder college exam questions with imagesMMMU-Pro+6.2points ahead
Every test, side by side
All 62 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- Terminal-Bench 2.1Claude Sonnet 4.5 by 27.355.828.5+27.3
- LMArena · WebDevClaude Sonnet 4.5 by 170 rating points13941224+170 rating
- SWE-bench VerifiedClaude Sonnet 4.5 by 1477.263.2+14
- Terminal-Bench HardClaude Sonnet 4.5 by 9.135.626.5+9.1
- SciCodetie45.746.3tie
AgentsClaude Sonnet 4.5
- GDPValClaude Sonnet 4.5 by 20.520.50+20.5
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 14.824.59.7+14.8
- BrowseCompClaude Sonnet 4.5 by 14.224.19.9+14.2
- Terminal-Bench 4.0tie00tie
ReasoningClaude Sonnet 4.5
- ARC-AGI-2Claude Sonnet 4.5 by 8.713.64.9+8.7
- SimpleBenchClaude Sonnet 4.5 by 2.754.351.6+2.7
- CritPtGemini 2.5 Pro by 1.51.12.6+1.5
- GPQA Diamondtie83.483.6tie
- Humanity's Last Examtie17.818tie
FactsGemini 2.5 Pro
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 41.850.99.1+41.8
- SimpleQA VerifiedGemini 2.5 Pro by 25.330.756+25.3
- AA-Omniscience · AccuracyGemini 2.5 Pro by 6.232.939+6.2
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 5127+5
Images and chartsGemini 2.5 Pro
MathClaude Sonnet 4.5
- FrontierMath Tier 4Claude Sonnet 4.5 by 2.42.40+2.4
- FrontierMath Tiers 1-3 (v2)tie23.924.6tie
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 3.372.369+3.3
- LongBench v2Claude Sonnet 4.5 by 361.858.8+3
Following instructionsClaude Sonnet 4.5
- IFBenchClaude Sonnet 4.5 by 8.657.348.7+8.6
- Multi-ChallengeClaude Sonnet 4.5 by 1.755.353.6+1.7
Other results35 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-BenchClaude Sonnet 4.5 by 449854+44
- MRCRGemini 2.5 Pro by 37.655.493+37.6
- ARC-AGI-1Claude Sonnet 4.5 by 26.763.737+26.7
- HarmBenchClaude Sonnet 4.5 by 26.69265.4+26.6
- Terminal-BenchClaude Sonnet 4.5 by 24.75025.3+24.7
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 2478.154.1+24
- TAU-bench (airline)Claude Sonnet 4.5 by 207050+20
- TAU-bench (retail)Claude Sonnet 4.5 by 19.286.267+19.2
- FinSearchComp-globalClaude Sonnet 4.5 by 18.260.842.6+18.2
- AA-OmniscienceClaude Sonnet 4.5 by 16.2-0.1-16.4+16.2
- AIR-Bench 2024Claude Sonnet 4.5 by 16.289.873.6+16.2
- AA Agentic IndexClaude Sonnet 4.5 by 1417.53.5+14
- HMMT Feb. 2025Gemini 2.5 Pro by 13.367.580.8+13.3
- GAIA (text only)Claude Sonnet 4.5 by 1171.260.2+11
- BrowseComp-ZHClaude Sonnet 4.5 by 10.242.432.2+10.2
- xbench-DeepSearchClaude Sonnet 4.5 by 106656+10
- HMMT 2025Claude Sonnet 4.5 by 8.974.665.7+8.9
- AA IntelligenceClaude Sonnet 4.5 by 5.720.715+5.7
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 5.452.146.7+5.4
- vectara_factual_consistencyGemini 2.5 Pro by 58893+5
- AIME 2025Claude Sonnet 4.5 by 48783+4
- ArtifactsBenchClaude Sonnet 4.5 by 3.861.557.7+3.8
- HLE (with tools)Claude Sonnet 4.5 by 3.63228.4+3.6
- vectara_answer_rateGemini 2.5 Pro by 3.595.699.1+3.5
- LiveCodeBenchGemini 2.5 Pro by 3.27174.2+3.2
- simple_safety_testsClaude Sonnet 4.5 by 310097+3
- bbqClaude Sonnet 4.5 by 2.598.996.4+2.5
- XSTestGemini 2.5 Pro by 2.396.498.7+2.3
- vectara_avg_summary_lengthClaude Sonnet 4.5 by 21.4 rating points127.8106.4+21.4 rating
- HMMT Nov. 2025Claude Sonnet 4.5 by 1.781.780+1.7
- theagentcompanyClaude Sonnet 4.5 by 1.74139.3+1.7
- MMLU-ProClaude Sonnet 4.5 by 1.587.586+1.5
- matharena_visual_math_overallGemini 2.5 Pro by 1.475.877.2+1.4
- anthropic_red_teamGemini 2.5 Pro by 1.398.299.5+1.3
- frontiermath_tier_4_v1tie4.24.2tie
Questions people ask
Which is better, Claude Sonnet 4.5 or Gemini 2.5 Pro?
Claude Sonnet 4.5 wins six of the eight areas we test: coding, agents, reasoning, math, long documents and following instructions. Gemini 2.5 Pro wins facts and images and charts, and costs 38% less.
Which is better for coding?
Claude Sonnet 4.5. It wins 4 of the 5 coding tests both models report; Gemini 2.5 Pro wins none, and 1 is a tie.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. That makes Gemini 2.5 Pro about 38% cheaper for the same work.
How do you compare the two?
We use the 62 benchmark tests both models have published scores on. The verdict counts the 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 35 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.