GPT-5.2 vs Qwen3 VL 4B (Reasoning)
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
GPT-5.2 is the stronger all-rounder.
Scores updated · 29 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.
- Images and chartsUnderstanding pictures, charts and video40GPT-5.24 of 5 tests · 1 tie
- ReasoningHard problems that need careful thinking30GPT-5.23 of 3 tests
- CodingWriting and fixing software20GPT-5.22 of 2 tests
- FactsGetting facts right instead of making them up20GPT-5.22 of 2 tests
- AgentsCarrying out multi-step tasks on its own10GPT-5.21 of 1 test
- Long documentsFinding answers in very long texts10GPT-5.21 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-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.
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+61.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+45.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+40.9points ahead
Where Qwen3 VL 4B (Reasoning) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 29 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 45.5471.5+45.5
- SciCodeGPT-5.2 by 3552.117.1+35
ReasoningGPT-5.2
- GPQA DiamondGPT-5.2 by 40.990.349.4+40.9
- Humanity's Last ExamGPT-5.2 by 33.137.74.6+33.1
- CritPtGPT-5.2 by 11.611.60+11.6
FactsGPT-5.2
- AA-Omniscience · AccuracyGPT-5.2 by 32.144.312.2+32.1
- AA-Omniscience · Non-hallucinationGPT-5.2 by 10.618.88.2+10.6
Images and chartsGPT-5.2
- CharXiv (RQ)GPT-5.2 by 31.882.150.3+31.8
- Video-MMEGPT-5.2 by 26.38659.7+26.3
- MMMU-ProGPT-5.2 by 22.674.652+22.6
- MathVistaGPT-5.2 by 3.382.879.5+3.3
- OCRBenchtie80.780.8tie
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.
- τ²-Bench Telecom (AA run)GPT-5.2 by 69.384.815.5+69.3
- AA-OmniscienceGPT-5.2 by 67.5-0.9-68.4+67.5
- HMMT 2025GPT-5.2 by 46.399.453.1+46.3
- AA Agentic IndexGPT-5.2 by 45.860.214.4+45.8
- Artificial Analysis Coding IndexGPT-5.2 by 4248.76.7+42
- LiveCodeBenchGPT-5.2 by 37.78951.3+37.7
- ScreenSpot-Pro (No tools)GPT-5.2 by 37.186.349.2+37.1
- AIME 2025GPT-5.2 by 25.510074.5+25.5
- AA IntelligenceGPT-5.2 by 23.430.47+23.4
- MATH-VisionGPT-5.2 by 238360+23
- LongVideoBenchGPT-5.2 by 18.876.557.7+18.8
- VideoMMMUGPT-5.2 by 16.585.969.4+16.5
- MMLU-ProGPT-5.2 by 13.186.773.6+13.1
- InfoVQA (val)GPT-5.2 by 4.58479.5+4.5
Questions people ask
Which is better, GPT-5.2 or Qwen3 VL 4B (Reasoning)?
GPT-5.2 wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Qwen3 VL 4B (Reasoning) wins none.
Which is better for coding?
GPT-5.2. It wins 2 of the 2 coding tests both models report; Qwen3 VL 4B (Reasoning) wins none.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 15 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.