DeepSeek-V3 vs LongCat Flash Lite
Wins 3 of 6 areas
Coding · Facts · Long documents
Wins 2 of 6 areas
Agents · Following instructions
DeepSeek-V3 wins more areas, narrowly.LongCat Flash Lite is better at agents.
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.
- FactsGetting facts right instead of making them up20DeepSeek-V32 of 2 tests
- CodingWriting and fixing software21DeepSeek-V32 of 3 tests
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- AgentsCarrying out multi-step tasks on its own01LongCat Flash Lite1 of 1 test
- Following instructionsDoing exactly what it is asked01LongCat Flash Lite1 of 1 test
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
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.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-V3 pulls ahead
- Reasons across sets of long documentsAA-LCR+12.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+12.2points ahead
- Code for real scientific research problemsSciCode+10.6points ahead
Where LongCat Flash Lite pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+12.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.1points ahead
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.
CodingDeepSeek-V3
- SWE-bench VerifiedLongCat Flash Lite by 12.44254.4+12.4
- SciCodeDeepSeek-V3 by 10.63928.4+10.6
- Terminal-Bench HardDeepSeek-V3 by 4.615.210.6+4.6
ReasoningEven
- GPQA DiamondDeepSeek-V3 by 1.965.563.6+1.9
- Humanity's Last ExamLongCat Flash Lite by 1.14.75.8+1.1
- CritPttie00tie
FactsDeepSeek-V3
- AA-Omniscience · AccuracyDeepSeek-V3 by 12.225.413.3+12.2
- AA-Omniscience · Non-hallucinationDeepSeek-V3 by 10.314.13.8+10.3
Following instructionsLongCat Flash Lite
- IFBenchLongCat Flash Lite by 2.14143.1+2.1
Other results10 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)LongCat Flash Lite by 32.447.179.5+32.4
- AA-OmniscienceDeepSeek-V3 by 29.4-40.7-70.1+29.4
- Tau2 airlineLongCat Flash Lite by 193958+19
- AIME 2025LongCat Flash Lite by 11.951.363.2+11.9
- MATH-500 (EM)LongCat Flash Lite by 6.690.296.8+6.6
- Artificial Analysis Coding IndexDeepSeek-V3 by 6.52316.5+6.5
- CMMLUDeepSeek-V3 by 6.388.882.5+6.3
- τ²-Bench (Retail)LongCat Flash Lite by 469.173.1+4
- MMLU-ProLongCat Flash Lite by 2.475.978.3+2.4
- AA IntelligenceLongCat Flash Lite by 1.89.711.5+1.8
Questions people ask
Which is better, DeepSeek-V3 or LongCat Flash Lite?
DeepSeek-V3 wins three of the six areas where both have results: coding, facts and long documents. LongCat Flash Lite wins agents and following instructions. They are level on reasoning.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 3 coding tests both models report; LongCat Flash Lite wins 1.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.