GPT-5 vs Qwen3.6 35B A3B
Wins 5 of 8 areas
Agents · Reasoning · Images and charts · Long documents · Following instructions
Wins 1 of 8 areas
Coding
GPT-5 is the stronger all-rounder.Qwen3.6 35B A3B is cheaper and better at coding.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- AgentsCarrying out multi-step tasks on its own30GPT-53 of 3 tests
- ReasoningHard problems that need careful thinking30GPT-53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video21GPT-52 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts10GPT-51 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-51 of 1 test
- CodingWriting and fixing software34Qwen3.6 35B A3B4 of 7 tests
- FactsGetting facts right instead of making them up11Even1 each
- MathCompetition and research-level math11Even1 each
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.
Qwen3.6 35B A3B 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 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+35points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+21.5points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+12.8points ahead
Where Qwen3.6 35B A3B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+31.7points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+11.9points ahead
- Reads and reasons about text in imagesOCRBenchv2+10points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 35B A3B
- SWE-bench MultilingualQwen3.6 35B A3B by 11.955.367.2+11.9
- Terminal-Bench 2.1Qwen3.6 35B A3B by 9.735.244.9+9.7
- SWE-bench ProQwen3.6 35B A3B by 7.741.849.5+7.7
- LiveCodeBench v6GPT-5 by 6.68780.4+6.6
- SciCodeGPT-5 by 6.342.936.6+6.3
- Terminal-Bench HardQwen3.6 35B A3B by 2.232.634.8+2.2
- SWE-bench VerifiedGPT-5 by 1.574.973.4+1.5
AgentsGPT-5
- τ-Bench V3 · BankingGPT-5 by 12.822.19.3+12.8
- BrowseCompGPT-5 by 6.254.948.7+6.2
- GDPValGPT-5 by 1.22119.8+1.2
ReasoningGPT-5
- Humanity's Last ExamGPT-5 by 6.328.522.2+6.3
- CritPtGPT-5 by 5.45.70.3+5.4
- GPQA DiamondGPT-5 by 1.385.484.1+1.3
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.6 35B A3B by 31.717.849.5+31.7
- AA-Omniscience · AccuracyGPT-5 by 21.540.318.8+21.5
Images and chartsGPT-5
- OCRBenchv2Qwen3.6 35B A3B by 1055.565.5+10
- CharXiv (RQ)GPT-5 by 3.181.178+3.1
- MMMUGPT-5 by 2.584.281.7+2.5
- MMMU-Protie74.275tie
MathEven
- FrontierMath Tiers 1-3 (v2)GPT-5 by 3555.420.4+35
- IMOAnswerBenchQwen3.6 35B A3B by 2.97678.9+2.9
Other results13 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.
- Terminal-Bench 2.0Qwen3.6 35B A3B by 16.335.251.5+16.3
- AA-OmniscienceGPT-5 by 13.5-8.7-22.2+13.5
- AA Agentic IndexGPT-5 by 11.526.515+11.5
- τ²-Bench Telecom (AA run)Qwen3.6 35B A3B by 10.584.895.3+10.5
- AA IntelligenceGPT-5 by 4.82318.2+4.8
- HMMT 2025GPT-5 by 4.293.389.1+4.2
- Artificial Analysis Coding IndexQwen3.6 35B A3B by 4.137.841.9+4.1
- HMMT Feb. 2025Qwen3.6 35B A3B by 2.488.390.7+2.4
- MMLU-ReduxGPT-5 by 295.393.3+2
- MMLU-ProGPT-5 by 1.987.185.2+1.9
- VideoMMMUtie84.683.7tie
- GPQA (unspecified)tie85.786tie
- HMMT Nov. 2025tie89.289.1tie
Questions people ask
Which is better, GPT-5 or Qwen3.6 35B A3B?
GPT-5 wins five of the eight areas we test: agents, reasoning, images and charts, long documents and following instructions. Qwen3.6 35B A3B wins coding, and costs 77% less. They are level on facts and math.
Which is better for coding?
Qwen3.6 35B A3B. It wins 4 of the 7 coding tests both models report; GPT-5 wins 3.
Which is cheaper?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3.6 35B A3B costs $0.38 and $2.25. That makes Qwen3.6 35B A3B about 77% cheaper for the same work.
How do you compare the two?
We use the 36 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 13 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.