EXAONE 4.5 33B vs Gemma 4 26B A4B
Wins 1 of 8 areas
Math
Wins 4 of 8 areas
Agents · Reasoning · Long documents · Following instructions
Gemma 4 26B A4B wins more areas, narrowly.EXAONE 4.5 33B is better at math.
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.
- ReasoningHard problems that need careful thinking01Gemma 4 26B A4B1 of 3 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own01Gemma 4 26B A4B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Gemma 4 26B A4B1 of 1 test
- Following instructionsDoing exactly what it is asked01Gemma 4 26B A4B1 of 1 test
- MathCompetition and research-level math10EXAONE 4.5 33B1 of 1 test
- CodingWriting and fixing software22Even2 each
- FactsGetting facts right instead of making them up11Even1 each
- Images and chartsUnderstanding pictures, charts and video11Even1 each · 1 tie
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 three tests each model wins by the widest margin. Scores are out of 100.
Where Gemma 4 26B A4B pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+17.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.4points ahead
- Code for real scientific research problemsSciCode+12points ahead
Where EXAONE 4.5 33B pulls ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+6.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.5points ahead
- Math problems shown in pictures and chartsMathVista+5.6points 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.
CodingEven
- Terminal-Bench 2.1Gemma 4 26B A4B by 17.721.339+17.7
- SciCodeGemma 4 26B A4B by 122840+12
- Terminal-Bench HardEXAONE 4.5 33B by 6.920.513.6+6.9
- LiveCodeBench v6EXAONE 4.5 33B by 4.381.477.1+4.3
AgentsGemma 4 26B A4B
- GDPValGemma 4 26B A4B by 3.403.4+3.4
- τ-Bench V3 · Bankingtie11.112tie
ReasoningGemma 4 26B A4B
- Humanity's Last ExamGemma 4 26B A4B by 6.412.919.3+6.4
- CritPttie0.30tie
- GPQA Diamondtie79.479.2tie
FactsEven
- AA-Omniscience · Non-hallucinationEXAONE 4.5 33B by 6.520.113.6+6.5
- AA-Omniscience · AccuracyGemma 4 26B A4B by 2.916.219.1+2.9
Images and chartsEven
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 14.45872.4+14.4
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.
- τ²-Bench Telecom (AA run)EXAONE 4.5 33B by 34.578.143.6+34.5
- Artificial Analysis Coding IndexGemma 4 26B A4B by 15.723.639.3+15.7
- AA IntelligenceGemma 4 26B A4B by 3.513.216.7+3.5
- IFEvalGemma 4 26B A4B by 1.889.691.4+1.8
- AA Agentic IndexGemma 4 26B A4B by 1.39.711+1.3
- AI2Dtie8988.3tie
- MMLU-Protie83.382.6tie
- AA-Omnisciencetie-50.7-50.8tie
Questions people ask
Which is better, EXAONE 4.5 33B or Gemma 4 26B A4B?
Gemma 4 26B A4B wins four of the eight areas we test: agents, reasoning, long documents and following instructions. EXAONE 4.5 33B wins math. They are level on coding, facts and images and charts.
Which is better for coding?
Neither. They win 2 coding tests each of the 4 both models report.
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.