Claude Opus 4.5 vs DeepSeek-V3
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude Opus 4.5 is the stronger all-rounder.DeepSeek-V3 is cheaper.
Scores updated · 33 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 Opus 4.54 of 4 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.53 of 3 tests
- Long documentsFinding answers in very long texts20Claude Opus 4.52 of 2 tests
- Following instructionsDoing exactly what it is asked20Claude Opus 4.52 of 2 tests
- FactsGetting facts right instead of making them up21Claude Opus 4.52 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Claude Opus 4.51 of 1 test
Agents rests on a single test.
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-V3 costs 96% 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 Opus 4.5 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+38.9points ahead
- Recent programming contest problemsLiveCodeBench v6+37.9points ahead
- Reasons across sets of long documentsAA-LCR+36.6points ahead
Where DeepSeek-V3 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.5
- SWE-bench VerifiedClaude Opus 4.5 by 38.980.942+38.9
- LiveCodeBench v6Claude Opus 4.5 by 37.984.846.9+37.9
- Terminal-Bench HardClaude Opus 4.5 by 31.84715.2+31.8
- SciCodeClaude Opus 4.5 by 10.549.539+10.5
ReasoningClaude Opus 4.5
- Humanity's Last ExamClaude Opus 4.5 by 25.430.14.7+25.4
- GPQA DiamondClaude Opus 4.5 by 21.186.665.5+21.1
- CritPtClaude Opus 4.5 by 4.64.60+4.6
FactsClaude Opus 4.5
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 24.93914.1+24.9
- AA-Omniscience · AccuracyClaude Opus 4.5 by 21.146.625.4+21.1
- Vectara HHEM hallucination ratelower is betterDeepSeek-V3 by 4.810.96.1+4.8
Long documentsClaude Opus 4.5
- AA-LCRClaude Opus 4.5 by 36.677.340.7+36.6
- LongBench v2Claude Opus 4.5 by 15.764.448.7+15.7
Following instructionsClaude Opus 4.5
- Multi-ChallengeClaude Opus 4.5 by 27.65931.4+27.6
- IFBenchClaude Opus 4.5 by 175841+17
Other results18 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 Opus 4.5 by 65.798.232.5+65.7
- HMMT Feb. 2025Claude Opus 4.5 by 63.792.929.2+63.7
- AA-OmniscienceClaude Opus 4.5 by 54.714-40.7+54.7
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 42.489.547.1+42.4
- AIME 2025Claude Opus 4.5 by 41.592.851.3+41.5
- LiveCodeBenchClaude Opus 4.5 by 37.88749.2+37.8
- Artificial Analysis Coding IndexClaude Opus 4.5 by 24.847.823+24.8
- τ²-Bench (Retail)Claude Opus 4.5 by 19.888.969.1+19.8
- AA IntelligenceClaude Opus 4.5 by 19.429.19.7+19.4
- SuperGPQAClaude Opus 4.5 by 16.970.653.7+16.9
- MMLU-ProClaude Opus 4.5 by 13.689.575.9+13.6
- MMMLUClaude Opus 4.5 by 11.490.879.4+11.4
- MMLU-ReduxClaude Opus 4.5 by 6.595.689.1+6.5
- C-EvalClaude Opus 4.5 by 5.792.286.5+5.7
- vectara_factual_consistencyDeepSeek-V3 by 4.889.193.9+4.8
- LiveBenchClaude Opus 4.5 by 3.67672.4+3.6
- vectara_avg_summary_lengthClaude Opus 4.5 by 32.8 rating points114.581.7+32.8 rating
- vectara_answer_rateClaude Opus 4.5 by 1.298.797.5+1.2
Questions people ask
Which is better, Claude Opus 4.5 or DeepSeek-V3?
Claude Opus 4.5 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. DeepSeek-V3 wins none, but costs 96% less.
Which is better for coding?
Claude Opus 4.5. It wins 4 of the 4 coding tests both models report; DeepSeek-V3 wins none.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; DeepSeek-V3 costs $0.24 and $0.90. That makes DeepSeek-V3 about 96% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.