Claude Sonnet 4.5 vs DeepSeek-R1 0528
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.DeepSeek-R1 0528 is cheaper.
Scores updated · 38 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 4.54 of 4 tests
- ReasoningHard problems that need careful thinking30Claude Sonnet 4.53 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up30Claude Sonnet 4.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 4.52 of 2 tests
- 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
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.
DeepSeek-R1 0528 costs 76% 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
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+36.5points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+32.6points ahead
Where DeepSeek-R1 0528 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- SWE-bench MultilingualClaude Sonnet 4.5 by 36.56730.5+36.5
- SWE-bench VerifiedClaude Sonnet 4.5 by 32.677.244.6+32.6
- Terminal-Bench HardClaude Sonnet 4.5 by 19.735.615.9+19.7
- SciCodeClaude Sonnet 4.5 by 5.445.740.3+5.4
AgentsClaude Sonnet 4.5
- BrowseCompClaude Sonnet 4.5 by 15.224.18.9+15.2
- GDPValClaude Sonnet 4.5 by 11.520.59+11.5
ReasoningClaude Sonnet 4.5
- SimpleBenchClaude Sonnet 4.5 by 13.554.340.8+13.5
- GPQA DiamondClaude Sonnet 4.5 by 2.183.481.3+2.1
- Humanity's Last ExamClaude Sonnet 4.5 by 217.815.8+2
- CritPttie1.11.4tie
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 34.350.916.6+34.3
- SimpleQA VerifiedClaude Sonnet 4.5 by 3.330.727.4+3.3
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 2.432.930.5+2.4
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 16.672.355.7+16.6
- LongBench v2Claude Sonnet 4.5 by 9.761.852.1+9.7
Following instructionsClaude Sonnet 4.5
- IFBenchClaude Sonnet 4.5 by 17.757.339.6+17.7
- Multi-ChallengeClaude Sonnet 4.5 by 10.355.345+10.3
Other results21 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.
- Terminal-BenchClaude Sonnet 4.5 by 44.3505.7+44.3
- ARC-AGI-1Claude Sonnet 4.5 by 42.563.721.2+42.5
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 41.678.136.5+41.6
- HarmBenchClaude Sonnet 4.5 by 37.49254.6+37.4
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 28.152.124+28.1
- AA-OmniscienceClaude Sonnet 4.5 by 27.3-0.1-27.4+27.3
- TAU-bench (retail)Claude Sonnet 4.5 by 22.386.263.9+22.3
- TAU-bench (airline)Claude Sonnet 4.5 by 16.57053.5+16.5
- HMMT Feb. 2025DeepSeek-R1 0528 by 9.267.576.7+9.2
- AA IntelligenceClaude Sonnet 4.5 by 7.620.713.1+7.6
- BrowseComp-ZHClaude Sonnet 4.5 by 6.742.435.7+6.7
- HMMT 2025DeepSeek-R1 0528 by 4.874.679.4+4.8
- AA Agentic IndexDeepSeek-R1 0528 by 3.317.520.8+3.3
- MMLU-ProClaude Sonnet 4.5 by 2.587.585+2.5
- bbqClaude Sonnet 4.5 by 2.498.996.5+2.4
- XSTestDeepSeek-R1 0528 by 2.496.498.8+2.4
- LiveCodeBenchDeepSeek-R1 0528 by 2.37173.3+2.3
- MMLU-ReduxClaude Sonnet 4.5 by 2.295.693.4+2.2
- simple_safety_testsClaude Sonnet 4.5 by 1.710098.3+1.7
- anthropic_red_teamtie98.299.1tie
- AIME 2025tie8787.5tie
Questions people ask
Which is better, Claude Sonnet 4.5 or DeepSeek-R1 0528?
Claude Sonnet 4.5 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. DeepSeek-R1 0528 wins none, but costs 76% less.
Which is better for coding?
Claude Sonnet 4.5. It wins 4 of the 4 coding tests both models report; DeepSeek-R1 0528 wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek-R1 0528 costs $1.35 and $3.00. That makes DeepSeek-R1 0528 about 76% cheaper for the same work.
How do you compare the two?
We use the 38 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 21 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.