GPT-5.2 vs Qwen3.5 122B A10B
Wins 4 of 7 areas
Coding · Agents · Reasoning · Facts
Wins 1 of 7 areas
Images and charts
GPT-5.2 wins more areas, narrowly.Qwen3.5 122B A10B is cheaper and better at images and charts.
Scores updated · 42 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 software51GPT-5.25 of 6 tests
- ReasoningHard problems that need careful thinking30GPT-5.23 of 3 tests
- FactsGetting facts right instead of making them up20GPT-5.22 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own21GPT-5.22 of 3 tests
- Images and chartsUnderstanding pictures, charts and video12Qwen3.5 122B A10B2 of 5 tests · 2 ties
- Long documentsFinding answers in very long texts11Even1 each
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Following instructions rests on a single test.
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.
Qwen3.5 122B A10B costs 77% 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-5.2 pulls ahead
- Real work tasks from 44 professionsGDPVal+32.6points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+19.9points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+15.9points ahead
Where Qwen3.5 122B A10B pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+15points ahead
- Reads text in imagesOCRBench+11.4points ahead
- Questions about very long textsLongBench v2+5.7points ahead
Every test, side by side
All 42 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 15.94731.1+15.9
- SWE-bench ProQwen3.5 122B A10B by 1529.944.9+15
- SciCodeGPT-5.2 by 12.452.139.7+12.4
- SWE-bench VerifiedGPT-5.2 by 88072+8
- LMArena · WebDevGPT-5.2 by 57 rating points14171360+57 rating
- SWE-bench MultilingualGPT-5.2 by 4.766.762+4.7
AgentsGPT-5.2
- GDPValGPT-5.2 by 32.648.315.7+32.6
- τ-Bench V3 · BankingQwen3.5 122B A10B by 4.211.115.3+4.2
- BrowseCompGPT-5.2 by 265.863.8+2
ReasoningGPT-5.2
- Humanity's Last ExamGPT-5.2 by 12.537.725.2+12.5
- CritPtGPT-5.2 by 1111.60.6+11
- GPQA DiamondGPT-5.2 by 4.690.385.7+4.6
FactsGPT-5.2
- AA-Omniscience · AccuracyGPT-5.2 by 19.944.324.4+19.9
- AA-Omniscience · Non-hallucinationGPT-5.2 by 5.918.812.9+5.9
- Vectara HHEM hallucination ratelower is bettertie10.811.2tie
Images and chartsQwen3.5 122B A10B
- OCRBenchQwen3.5 122B A10B by 11.480.792.1+11.4
- CharXiv (RQ)GPT-5.2 by 4.982.177.2+4.9
- MathVistaQwen3.5 122B A10B by 4.682.887.4+4.6
- MMMU-Protie74.675tie
- LMArena · Visiontie12461245tie
Long documentsEven
- AA-LCRGPT-5.2 by 6.482.776.3+6.4
- LongBench v2Qwen3.5 122B A10B by 5.754.560.2+5.7
Other results19 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 IndexGPT-5.2 by 50.660.29.6+50.6
- AA-OmniscienceGPT-5.2 by 40.6-0.9-41.5+40.6
- ScreenSpot-Pro (No tools)GPT-5.2 by 15.986.370.4+15.9
- AA IntelligenceGPT-5.2 by 14.830.415.6+14.8
- vectara_avg_summary_lengthGPT-5.2 by 99.9 rating points186.386.4+99.9 rating
- HMMT 2025GPT-5.2 by 9.199.490.3+9.1
- τ²-Bench Telecom (AA run)Qwen3.5 122B A10B by 8.884.893.6+8.8
- MMVUGPT-5.2 by 6.180.874.7+6.1
- SimpleVQAQwen3.5 122B A10B by 5.955.861.7+5.9
- Terminal-Bench 2.0GPT-5.2 by 4.65449.4+4.6
- OmniDocBench 1.5Qwen3.5 122B A10B by 4.185.789.8+4.1
- VideoMMMUGPT-5.2 by 3.985.982+3.9
- MATH-VisionQwen3.5 122B A10B by 3.28386.2+3.2
- Artificial Analysis Coding IndexGPT-5.2 by 348.745.7+3
- MMMLUGPT-5.2 by 2.989.686.7+2.9
- vectara_factual_consistencytie89.288.8tie
- vectara_answer_ratetie10099.8tie
- MMLU-Protie86.786.7tie
- ZeroBenchtie99tie
Questions people ask
Which is better, GPT-5.2 or Qwen3.5 122B A10B?
GPT-5.2 wins four of the seven areas where both have results: coding, agents, reasoning and facts. Qwen3.5 122B A10B wins images and charts, and costs 77% less. They are level on long documents and following instructions.
Which is better for coding?
GPT-5.2. It wins 5 of the 6 coding tests both models report; Qwen3.5 122B A10B wins 1.
Which is cheaper?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; Qwen3.5 122B A10B costs $0.40 and $3.20. That makes Qwen3.5 122B A10B about 77% cheaper for the same work.
How do you compare the two?
We use the 42 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.