DeepSeek-R1 0528 vs LongCat Flash Lite
Wins 3 of 6 areas
Reasoning · Facts · Long documents
Wins 2 of 6 areas
Agents · Following instructions
DeepSeek-R1 0528 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.
- ReasoningHard problems that need careful thinking30DeepSeek-R1 05283 of 3 tests
- FactsGetting facts right instead of making them up20DeepSeek-R1 05282 of 2 tests
- Long documentsFinding answers in very long texts10DeepSeek-R1 05281 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
- CodingWriting and fixing software22Even2 each
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-R1 0528 pulls ahead
- Reasons across sets of long documentsAA-LCR+27.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+17.7points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+17.2points ahead
Where LongCat Flash Lite pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+9.8points ahead
- Real work tasks from 44 professionsGDPVal+7.8points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+7.6points 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.
CodingEven
- SciCodeDeepSeek-R1 0528 by 11.940.328.4+11.9
- SWE-bench VerifiedLongCat Flash Lite by 9.844.654.4+9.8
- SWE-bench MultilingualLongCat Flash Lite by 7.630.538.1+7.6
- Terminal-Bench HardDeepSeek-R1 0528 by 5.315.910.6+5.3
ReasoningDeepSeek-R1 0528
- GPQA DiamondDeepSeek-R1 0528 by 17.781.363.6+17.7
- Humanity's Last ExamDeepSeek-R1 0528 by 1015.85.8+10
- CritPtDeepSeek-R1 0528 by 1.41.40+1.4
FactsDeepSeek-R1 0528
- AA-Omniscience · AccuracyDeepSeek-R1 0528 by 17.230.513.3+17.2
- AA-Omniscience · Non-hallucinationDeepSeek-R1 0528 by 12.816.63.8+12.8
Long documentsDeepSeek-R1 0528
- AA-LCRDeepSeek-R1 0528 by 27.455.728.3+27.4
Following instructionsLongCat Flash Lite
- IFBenchLongCat Flash Lite by 3.539.643.1+3.5
Other results9 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 4336.579.5+43
- AA-OmniscienceDeepSeek-R1 0528 by 42.7-27.4-70.1+42.7
- Terminal-BenchLongCat Flash Lite by 28.15.733.8+28.1
- AIME 2025DeepSeek-R1 0528 by 24.387.563.2+24.3
- AA Agentic IndexLongCat Flash Lite by 1820.838.8+18
- Artificial Analysis Coding IndexDeepSeek-R1 0528 by 7.52416.5+7.5
- MMLU-ProDeepSeek-R1 0528 by 6.78578.3+6.7
- AA IntelligenceDeepSeek-R1 0528 by 1.613.111.5+1.6
- MATH-500 (EM)DeepSeek-R1 0528 by 1.29896.8+1.2
Questions people ask
Which is better, DeepSeek-R1 0528 or LongCat Flash Lite?
DeepSeek-R1 0528 wins three of the six areas where both have results: reasoning, facts and long documents. LongCat Flash Lite wins agents and following instructions. They are level on coding.
Which is better for coding?
Neither. They win 2 coding tests each of the 4 both models report.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.