EXAONE 4.5 33B vs Qwen3.5 4B
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 1 of 8 areas
Long documents
EXAONE 4.5 33B is the stronger all-rounder.Qwen3.5 4B is better at long documents.
Scores updated · 25 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.
- Images and chartsUnderstanding pictures, charts and video40EXAONE 4.5 33B4 of 4 tests
- CodingWriting and fixing software31EXAONE 4.5 33B3 of 4 tests
- ReasoningHard problems that need careful thinking20EXAONE 4.5 33B2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20EXAONE 4.5 33B2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10EXAONE 4.5 33B1 of 1 test
- MathCompetition and research-level math10EXAONE 4.5 33B1 of 1 test
- Following instructionsDoing exactly what it is asked10EXAONE 4.5 33B1 of 1 test
- Long documentsFinding answers in very long texts01Qwen3.5 4B1 of 1 test
Agents, math, 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 EXAONE 4.5 33B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+25.6points ahead
- Math problems shown in pictures and chartsMathVista+21.4points ahead
- Questions that truly need the image to answerMMStar+15.6points ahead
Where Qwen3.5 4B pulls ahead
- Reasons across sets of long documentsAA-LCR+8.3points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+4.5points ahead
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEXAONE 4.5 33B
- LiveCodeBench v6EXAONE 4.5 33B by 25.681.455.8+25.6
- SciCodeEXAONE 4.5 33B by 11.92816.1+11.9
- Terminal-Bench 2.1Qwen3.5 4B by 4.521.325.8+4.5
- Terminal-Bench HardEXAONE 4.5 33B by 2.320.518.2+2.3
ReasoningEXAONE 4.5 33B
- Humanity's Last ExamEXAONE 4.5 33B by 312.99.9+3
- GPQA DiamondEXAONE 4.5 33B by 2.379.477.1+2.3
- CritPttie0.30tie
FactsEXAONE 4.5 33B
- AA-Omniscience · Non-hallucinationEXAONE 4.5 33B by 6.720.113.4+6.7
- AA-Omniscience · AccuracyEXAONE 4.5 33B by 1.116.215.1+1.1
Images and chartsEXAONE 4.5 33B
Following instructionsEXAONE 4.5 33B
- IFBenchEXAONE 4.5 33B by 65852+6
Other results8 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 IndexQwen3.5 4B by 22.89.732.5+22.8
- τ²-Bench Telecom (AA run)Qwen3.5 4B by 1478.192.1+14
- AA-OmniscienceEXAONE 4.5 33B by 7.6-50.7-58.4+7.6
- τ²-Bench (Retail)EXAONE 4.5 33B by 677.971.9+6
- MMLU-ProEXAONE 4.5 33B by 4.283.379.1+4.2
- IFEvalEXAONE 4.5 33B by 3.489.686.2+3.4
- Artificial Analysis Coding IndexEXAONE 4.5 33B by 123.622.6+1
- AA Intelligencetie13.213.1tie
Questions people ask
Which is better, EXAONE 4.5 33B or Qwen3.5 4B?
EXAONE 4.5 33B wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. Qwen3.5 4B wins long documents.
Which is better for coding?
EXAONE 4.5 33B. It wins 3 of the 4 coding tests both models report; Qwen3.5 4B wins 1.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.