GPT-5.4 vs Qwen3.6 35B A3B
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
GPT-5.4 is the stronger all-rounder.Qwen3.6 35B A3B is cheaper.
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.
- CodingWriting and fixing software50GPT-5.45 of 5 tests
- AgentsCarrying out multi-step tasks on its own40GPT-5.44 of 4 tests
- MathCompetition and research-level math40GPT-5.44 of 4 tests
- ReasoningHard problems that need careful thinking30GPT-5.43 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-5.42 of 2 tests
- Long documentsFinding answers in very long texts10GPT-5.41 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.41 of 1 test
- FactsGetting facts right instead of making them up11Even1 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 85% 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-5.4 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+58.2points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+34points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+33.4points ahead
Where Qwen3.6 35B A3B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+41.2points 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.
CodingGPT-5.4
- Terminal-Bench 2.1GPT-5.4 by 33.478.344.9+33.4
- Terminal-Bench HardGPT-5.4 by 22.857.634.8+22.8
- SciCodeGPT-5.4 by 2056.636.6+20
- SWE-bench ProGPT-5.4 by 8.257.749.5+8.2
- SWE-bench MultilingualGPT-5.4 by 4.571.767.2+4.5
AgentsGPT-5.4
- BrowseCompGPT-5.4 by 3482.748.7+34
- τ-Bench V3 · BankingGPT-5.4 by 30.339.69.3+30.3
- GDPValGPT-5.4 by 17.637.419.8+17.6
- MCP AtlasGPT-5.4 by 4.467.262.8+4.4
ReasoningGPT-5.4
- CritPtGPT-5.4 by 23.123.40.3+23.1
- Humanity's Last ExamGPT-5.4 by 21.543.722.2+21.5
- GPQA DiamondGPT-5.4 by 7.99284.1+7.9
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.6 35B A3B by 41.28.349.5+41.2
- AA-Omniscience · AccuracyGPT-5.4 by 32.150.918.8+32.1
Images and chartsGPT-5.4
- CharXiv (RQ)GPT-5.4 by 4.882.878+4.8
- MMMU-ProGPT-5.4 by 3.478.475+3.4
MathGPT-5.4
- FrontierMath Tiers 1-3 (v2)GPT-5.4 by 58.278.620.4+58.2
- HMMT Feb. 2026GPT-5.4 by 14.197.783.6+14.1
- IMOAnswerBenchGPT-5.4 by 12.591.478.9+12.5
- AIME 2026GPT-5.4 by 6.599.292.7+6.5
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.
- AA Agentic IndexGPT-5.4 by 29.244.215+29.2
- Artificial Analysis Coding IndexGPT-5.4 by 29.271.141.9+29.2
- AA-OmniscienceGPT-5.4 by 285.8-22.2+28
- Tool-DecathlonGPT-5.4 by 27.754.626.9+27.7
- ToolathlonGPT-5.4 by 27.754.626.9+27.7
- MCPMarkGPT-5.4 by 25.562.537+25.5
- Terminal-Bench 2.0GPT-5.4 by 23.675.151.5+23.6
- AA IntelligenceGPT-5.4 by 20.83918.2+20.8
- NL2RepoGPT-5.4 by 11.941.329.4+11.9
- τ²-Bench Telecom (AA run)Qwen3.6 35B A3B by 8.287.195.3+8.2
- HMMT Nov. 2025GPT-5.4 by 6.795.889.1+6.7
- τ³-BenchGPT-5.4 by 5.772.967.2+5.7
- MMLU-ProGPT-5.4 by 2.387.585.2+2.3
- OmniDocBench 1.5tie89.189.9tie
Questions people ask
Which is better, GPT-5.4 or Qwen3.6 35B A3B?
GPT-5.4 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Qwen3.6 35B A3B wins none, but costs 85% less. They are level on facts.
Which is better for coding?
GPT-5.4. It wins 5 of the 5 coding tests both models report; Qwen3.6 35B A3B wins none.
Which is cheaper?
GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; Qwen3.6 35B A3B costs $0.38 and $2.25. That makes Qwen3.6 35B A3B about 85% 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 22 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.