DeepSeek-V4-Flash vs GPT-5.1
Wins 4 of 6 areas
Coding · Agents · Reasoning · Following instructions
Wins 1 of 6 areas
Facts
DeepSeek-V4-Flash is the stronger all-rounder.GPT-5.1 is better at facts.
Scores updated · 28 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 software51DeepSeek-V4-Flash5 of 6 tests
- ReasoningHard problems that need careful thinking41DeepSeek-V4-Flash4 of 5 tests
- AgentsCarrying out multi-step tasks on its own30DeepSeek-V4-Flash3 of 3 tests
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Flash1 of 1 test
- FactsGetting facts right instead of making them up12GPT-5.12 of 3 tests
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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.
DeepSeek-V4-Flash costs 84% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-V4-Flash pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+43.8points ahead
- Real work tasks from 44 professionsGDPVal+30.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+26.3points ahead
Where GPT-5.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+39.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+13.9points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+9.9points ahead
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Flash
- Terminal-Bench 2.1DeepSeek-V4-Flash by 26.378.752.4+26.3
- Terminal-Bench HardGPT-5.1 by 9.935.645.5+9.9
- SciCodeDeepSeek-V4-Flash by 750.343.3+7
- LiveCodeBench v6DeepSeek-V4-Flash by 3.690.687+3.6
- LMArena · WebDevDeepSeek-V4-Flash by 35 rating points14301395+35 rating
- SWE-bench VerifiedDeepSeek-V4-Flash by 2.77976.3+2.7
AgentsDeepSeek-V4-Flash
- GDPValDeepSeek-V4-Flash by 30.446.916.5+30.4
- τ-Bench V3 · BankingDeepSeek-V4-Flash by 23.539.415.9+23.5
- BrowseCompDeepSeek-V4-Flash by 22.473.250.8+22.4
ReasoningDeepSeek-V4-Flash
- ARC-AGI-2DeepSeek-V4-Flash by 43.861.417.6+43.8
- CritPtDeepSeek-V4-Flash by 11.716.64.9+11.7
- Humanity's Last ExamDeepSeek-V4-Flash by 10.138.628.5+10.1
- SimpleBenchGPT-5.1 by 6.946.353.2+6.9
- GPQA DiamondDeepSeek-V4-Flash by 3.590.887.3+3.5
FactsGPT-5.1
- AA-Omniscience · Non-hallucinationGPT-5.1 by 39.88.348.1+39.8
- SimpleQA VerifiedGPT-5.1 by 13.934.148+13.9
- AA-Omniscience · AccuracyDeepSeek-V4-Flash by 2.740.437.7+2.7
Following instructionsDeepSeek-V4-Flash
- IFBenchDeepSeek-V4-Flash by 6.379.272.9+6.3
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.
- AA Agentic IndexDeepSeek-V4-Flash by 20.141.721.6+20.1
- AA-OmniscienceGPT-5.1 by 19.7-14.35.4+19.7
- Artificial Analysis Coding IndexDeepSeek-V4-Flash by 19.769.149.4+19.7
- ARC-AGI-1DeepSeek-V4-Flash by 16.28972.8+16.2
- τ²-Bench Telecom (AA run)DeepSeek-V4-Flash by 13.19581.9+13.1
- AA IntelligenceDeepSeek-V4-Flash by 9.634.324.7+9.6
- Terminal-Bench 2.0DeepSeek-V4-Flash by 9.356.947.6+9.3
- HLE (with tools)DeepSeek-V4-Flash by 2.445.142.7+2.4
- MMLU-Protie86.287tie
Questions people ask
Which is better, DeepSeek-V4-Flash or GPT-5.1?
DeepSeek-V4-Flash wins four of the six areas where both have results: coding, agents, reasoning and following instructions. GPT-5.1 wins facts. They are level on long documents.
Which is better for coding?
DeepSeek-V4-Flash. It wins 5 of the 6 coding tests both models report; GPT-5.1 wins 1.
Which is cheaper?
DeepSeek-V4-Flash costs $0.44 per million input tokens and $1.32 per million output tokens; GPT-5.1 costs $1.25 and $10.00. That makes DeepSeek-V4-Flash about 84% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 19 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.