GPT-5 vs Qwen3.6 Plus
Wins 1 of 8 areas
Facts
Wins 3 of 8 areas
Coding · Images and charts · Following instructions
Qwen3.6 Plus wins more areas, narrowly.GPT-5 is better at facts.
Scores updated · 37 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.
- CodingWriting and fixing software16Qwen3.6 Plus6 of 8 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video02Qwen3.6 Plus2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Qwen3.6 Plus1 of 1 test
- FactsGetting facts right instead of making them up21GPT-52 of 3 tests
- AgentsCarrying out multi-step tasks on its own11Even1 each
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
- MathCompetition and research-level math11Even1 each
- 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.
Qwen3.6 Plus costs 69% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.6 Plus pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+47.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+26.2points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+18.5points ahead
Where GPT-5 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+17.1points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+13.9points ahead
- Short factual questions, answered correctlySimpleQA Verified+6points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 Plus
- Terminal-Bench 2.1Qwen3.6 Plus by 26.235.261.4+26.2
- SWE-bench MultilingualQwen3.6 Plus by 18.555.373.8+18.5
- SWE-bench ProQwen3.6 Plus by 14.841.856.6+14.8
- Terminal-Bench HardQwen3.6 Plus by 11.332.643.9+11.3
- LMArena · WebDevQwen3.6 Plus by 43 rating points14181461+43 rating
- SWE-bench VerifiedQwen3.6 Plus by 3.974.978.8+3.9
- SciCodeGPT-5 by 2.242.940.7+2.2
- LiveCodeBench v6tie8787.1tie
AgentsEven
- GDPValQwen3.6 Plus by 3.72124.7+3.7
- τ-Bench V3 · BankingGPT-5 by 1.322.120.8+1.3
ReasoningEven
- CritPtGPT-5 by 2.85.72.9+2.8
- GPQA DiamondQwen3.6 Plus by 2.885.488.2+2.8
- Humanity's Last Examtie28.527.8tie
FactsGPT-5
- AA-Omniscience · Non-hallucinationQwen3.6 Plus by 47.617.865.4+47.6
- AA-Omniscience · AccuracyGPT-5 by 13.940.326.4+13.9
- SimpleQA VerifiedGPT-5 by 650.144.1+6
Images and chartsQwen3.6 Plus
- MMMU-ProQwen3.6 Plus by 3.874.278+3.8
- MMMUQwen3.6 Plus by 1.884.286+1.8
- CharXiv (RQ)tie81.181.5tie
MathEven
- FrontierMath Tiers 1-3 (v2)GPT-5 by 17.155.438.3+17.1
- IMOAnswerBenchQwen3.6 Plus by 7.87683.8+7.8
Following instructionsQwen3.6 Plus
- IFBenchQwen3.6 Plus by 2.173.175.2+2.1
Other results14 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 Plus by 26.435.261.6+26.4
- Artificial Analysis Coding IndexQwen3.6 Plus by 16.737.854.5+16.7
- HLE (with tools)Qwen3.6 Plus by 15.435.250.6+15.4
- τ²-Bench Telecom (AA run)Qwen3.6 Plus by 12.984.897.7+12.9
- AA-OmniscienceQwen3.6 Plus by 9.6-8.70.9+9.6
- HMMT Nov. 2025Qwen3.6 Plus by 5.489.294.6+5.4
- frontiermath_tier_4_v1GPT-5 by 4.212.58.3+4.2
- AA IntelligenceQwen3.6 Plus by 42327+4
- AA Agentic IndexQwen3.6 Plus by 2.526.529+2.5
- MMLU-ProQwen3.6 Plus by 1.487.188.5+1.4
- HMMT 2025Qwen3.6 Plus by 1.393.394.6+1.3
- MMLU-Reduxtie95.394.5tie
- VideoMMMUtie84.684tie
- ERQAtie65.765.7tie
Questions people ask
Which is better, GPT-5 or Qwen3.6 Plus?
Qwen3.6 Plus wins three of the eight areas we test: coding, images and charts and following instructions. GPT-5 wins facts. They are level on agents, reasoning, math and long documents.
Which is better for coding?
Qwen3.6 Plus. It wins 6 of the 8 coding tests both models report; GPT-5 wins 1, and 1 is a tie.
Which is cheaper?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 69% cheaper for the same work.
How do you compare the two?
We use the 37 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 14 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.