DeepSeek-V3.2-Speciale vs GPT-5.2
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
GPT-5.2 is the stronger all-rounder.DeepSeek-V3.2-Speciale is cheaper.
Scores updated · 23 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 software03GPT-5.23 of 3 tests
- ReasoningHard problems that need careful thinking13GPT-5.23 of 4 tests
- FactsGetting facts right instead of making them up02GPT-5.22 of 2 tests
- AgentsCarrying out multi-step tasks on its own01GPT-5.21 of 1 test
- Long documentsFinding answers in very long texts01GPT-5.21 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5.21 of 1 test
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.
DeepSeek-V3.2-Speciale costs 95% 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 GPT-5.2 pulls ahead
- Reasons across sets of long documentsAA-LCR+12.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+12.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.5points ahead
Where DeepSeek-V3.2-Speciale pulls ahead
- Common-sense trick questionsSimpleBench+6.8points ahead
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.2
- Terminal-Bench HardGPT-5.2 by 12.234.847+12.2
- SciCodeGPT-5.2 by 8.14452.1+8.1
- SWE-bench VerifiedGPT-5.2 by 6.973.180+6.9
ReasoningGPT-5.2
- Humanity's Last ExamGPT-5.2 by 928.737.7+9
- SimpleBenchDeepSeek-V3.2-Speciale by 6.852.645.8+6.8
- CritPtGPT-5.2 by 4.27.411.6+4.2
- GPQA DiamondGPT-5.2 by 3.287.190.3+3.2
FactsGPT-5.2
- AA-Omniscience · Non-hallucinationGPT-5.2 by 810.818.8+8
- AA-Omniscience · AccuracyGPT-5.2 by 6.537.844.3+6.5
Other results11 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)GPT-5.2 by 84.8084.8+84.8
- AA Agentic IndexGPT-5.2 by 60.2060.2+60.2
- AA-OmniscienceGPT-5.2 by 16.8-17.7-0.9+16.8
- AA IntelligenceGPT-5.2 by 15.914.530.4+15.9
- ToolathlonGPT-5.2 by 11.135.246.3+11.1
- Artificial Analysis Coding IndexGPT-5.2 by 10.837.948.7+10.8
- Terminal-Bench 2.0GPT-5.2 by 7.646.454+7.6
- AIME 2025GPT-5.2 by 496100+4
- HMMT Feb. 2025GPT-5.2 by 2.597.5100+2.5
- HMMT Nov. 2025GPT-5.2 by 2.593.395.8+2.5
- HMMT 2025tie99.299.4tie
Questions people ask
Which is better, DeepSeek-V3.2-Speciale or GPT-5.2?
GPT-5.2 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. DeepSeek-V3.2-Speciale wins none, but costs 95% less.
Which is better for coding?
GPT-5.2. It wins 3 of the 3 coding tests both models report; DeepSeek-V3.2-Speciale wins none.
Which is cheaper?
DeepSeek-V3.2-Speciale costs $0.29 per million input tokens and $0.43 per million output tokens; GPT-5.2 costs $1.75 and $14.00. That makes DeepSeek-V3.2-Speciale about 95% cheaper for the same work.
How do you compare the two?
We use the 23 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 11 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.