DeepSeek-V4-Pro vs GPT-5.6 Luna
Wins 1 of 7 areas
Following instructions
Wins 5 of 7 areas
Coding · Agents · Reasoning · Math · Long documents
GPT-5.6 Luna is the stronger all-rounder.DeepSeek-V4-Pro is better at following instructions.
Scores updated · 43 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software07GPT-5.6 Luna7 of 7 tests
- AgentsCarrying out multi-step tasks on its own14GPT-5.6 Luna4 of 6 tests · 1 tie
- ReasoningHard problems that need careful thinking14GPT-5.6 Luna4 of 5 tests
- MathCompetition and research-level math13GPT-5.6 Luna3 of 5 tests · 1 tie
- Long documentsFinding answers in very long texts01GPT-5.6 Luna1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 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.
GPT-5.6 Luna costs 73% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-5.6 Luna pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+56.1points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+36.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+16.9points ahead
Where DeepSeek-V4-Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+5.2points ahead
- Common-sense trick questionsSimpleBench+4.1points ahead
- Fresh competition math problemsLiveBench · Mathematics+3.5points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.6 Luna
- Terminal-Bench 2.1GPT-5.6 Luna by 16.96480.9+16.9
- LiveBench · CodingGPT-5.6 Luna by 12.97082.9+12.9
- SWE-bench VerifiedGPT-5.6 Luna by 12.480.693+12.4
- SWE-bench ProGPT-5.6 Luna by 7.355.462.7+7.3
- LiveBench · Agentic CodingGPT-5.6 Luna by 5.842.648.4+5.8
- LMArena · WebDevGPT-5.6 Luna by 56 rating points14631519+56 rating
- SciCodeGPT-5.6 Luna by 2.850.853.6+2.8
AgentsGPT-5.6 Luna
- GDPValGPT-5.6 Luna by 15.232.848+15.2
- AA ApexAgentsGPT-5.6 Luna by 11.524.335.8+11.5
- Terminal-Bench 4.0DeepSeek-V4-Pro by 314.611.6+3
- AA IT-Bench SREGPT-5.6 Luna by 238.340.3+2
- τ-Bench V3 · BankingGPT-5.6 Luna by 130.131.1+1
- BrowseComptie83.483.3tie
ReasoningGPT-5.6 Luna
- CritPtGPT-5.6 Luna by 7.712.920.6+7.7
- SimpleBenchDeepSeek-V4-Pro by 4.150.946.8+4.1
- LiveBench · ReasoningGPT-5.6 Luna by 2.982.785.6+2.9
- GPQA DiamondGPT-5.6 Luna by 2.388.891.1+2.3
- Humanity's Last ExamGPT-5.6 Luna by 237.539.5+2
FactsEven
- SimpleQA VerifiedDeepSeek-V4-Pro by 5.246.241+5.2
- AA-Omniscience · Non-hallucinationGPT-5.6 Luna by 1.55.97.4+1.5
- AA-Omniscience · Accuracytie4342.7tie
MathGPT-5.6 Luna
- FrontierMath Tier 4GPT-5.6 Luna by 56.12.458.5+56.1
- FrontierMath Tiers 1-3 (v2)GPT-5.6 Luna by 36.845.382.1+36.8
- LiveBench · MathematicsDeepSeek-V4-Pro by 3.590.787.2+3.5
- HMMT Feb. 2026GPT-5.6 Luna by 3.395.298.5+3.3
- AIME 2026tie96.797.6tie
Following instructionsDeepSeek-V4-Pro
- LiveBench · Instruction FollowingDeepSeek-V4-Pro by 2.362.460.1+2.3
Other results15 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.
- DeepSWEGPT-5.6 Luna by 54.412.867.2+54.4
- Agents' Last ExamGPT-5.6 Luna by 24.625.750.3+24.6
- GDPval-AA v2GPT-5.6 Luna by 224 rating points13061530+224 rating
- AA Agentic IndexGPT-5.6 Luna by 1527.742.7+15
- Artificial Analysis Coding IndexGPT-5.6 Luna by 1259.471.4+12
- Toolathlon VerifiedGPT-5.6 Luna by 1255.967.9+12
- HLE (with tools)DeepSeek-V4-Pro by 11.16048.9+11.1
- SWEBench Pro PublicGPT-5.6 Luna by 7.355.462.7+7.3
- AA IntelligenceGPT-5.6 Luna by 6.930.437.3+6.9
- livebench_languageDeepSeek-V4-Pro by 5.578.172.6+5.5
- Terminal-Bench 4.0GPT-5.6 Luna by 4.912.417.3+4.9
- livebench_data_analysisGPT-5.6 Luna by 3.574.578+3.5
- τ³-Bench BankingDeepSeek-V4-Pro by 1.72624.3+1.7
- ToolathlonGPT-5.6 Luna by 1.651.853.4+1.6
- AA-Omnisciencetie-10.7-10.3tie
Questions people ask
Which is better, DeepSeek-V4-Pro or GPT-5.6 Luna?
GPT-5.6 Luna wins five of the seven areas where both have results: coding, agents, reasoning, math and long documents. DeepSeek-V4-Pro wins following instructions. They are level on facts.
Which is better for coding?
GPT-5.6 Luna. It wins 7 of the 7 coding tests both models report; DeepSeek-V4-Pro wins none.
Which is cheaper?
DeepSeek-V4-Pro costs $1.32 per million input tokens and $3.96 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. That makes GPT-5.6 Luna about 73% cheaper for the same work.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 28 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.