Claude Sonnet 4.5 vs DeepSeek-V3.1-Terminus
Wins 5 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 0 of 6 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.DeepSeek-V3.1-Terminus is cheaper.
Scores updated · 21 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 software30Claude Sonnet 4.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 4.52 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking20Claude Sonnet 4.52 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Claude Sonnet 4.52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- Following instructionsDoing exactly what it is asked00Even0 each · 2 ties
Long documents 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-V3.1-Terminus costs 93% 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+25.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+10.9points ahead
- Real work tasks from 44 professionsGDPVal+9.9points ahead
Where DeepSeek-V3.1-Terminus pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 21 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 10.955.844.9+10.9
- SciCodeClaude Sonnet 4.5 by 7.745.738+7.7
- Terminal-Bench HardClaude Sonnet 4.5 by 5.335.630.3+5.3
AgentsClaude Sonnet 4.5
- GDPValClaude Sonnet 4.5 by 9.920.510.6+9.9
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 3.524.521+3.5
- Terminal-Bench 4.0tie00tie
ReasoningClaude Sonnet 4.5
- GPQA DiamondClaude Sonnet 4.5 by 4.283.479.2+4.2
- Humanity's Last ExamClaude Sonnet 4.5 by 1.417.816.4+1.4
- CritPttie1.11.7tie
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 25.750.925.2+25.7
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 5.232.927.7+5.2
Following instructionsEven
- Multi-Challengetie55.354.4tie
- IFBenchtie57.357tie
Other results7 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 4178.137.1+41
- AA-OmniscienceClaude Sonnet 4.5 by 26.3-0.1-26.4+26.3
- HMMT 2025DeepSeek-V3.1-Terminus by 11.574.686.1+11.5
- AA Agentic IndexClaude Sonnet 4.5 by 8.617.58.9+8.6
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 8.652.143.5+8.6
- AA IntelligenceClaude Sonnet 4.5 by 5.920.714.8+5.9
- LiveCodeBenchDeepSeek-V3.1-Terminus by 3.97174.9+3.9
Questions people ask
Which is better, Claude Sonnet 4.5 or DeepSeek-V3.1-Terminus?
Claude Sonnet 4.5 wins five of the six areas where both have results: coding, agents, reasoning, facts and long documents. DeepSeek-V3.1-Terminus wins none, but costs 93% less. They are level on following instructions.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 3 coding tests both models report; DeepSeek-V3.1-Terminus wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek-V3.1-Terminus costs $0.27 and $1.00. That makes DeepSeek-V3.1-Terminus about 93% cheaper for the same work.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.