EXAONE 4.5 33B vs Gemma 4 31B
Wins 1 of 8 areas
Math
Wins 6 of 8 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Gemma 4 31B is the stronger all-rounder.EXAONE 4.5 33B is better at math.
Scores updated · 24 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 thinking03Gemma 4 31B3 of 3 tests
- CodingWriting and fixing software13Gemma 4 31B3 of 4 tests
- AgentsCarrying out multi-step tasks on its own02Gemma 4 31B2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video12Gemma 4 31B2 of 3 tests
- Long documentsFinding answers in very long texts01Gemma 4 31B1 of 1 test
- Following instructionsDoing exactly what it is asked01Gemma 4 31B1 of 1 test
- MathCompetition and research-level math10EXAONE 4.5 33B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 31B pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+22.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.6points ahead
- Code for real scientific research problemsSciCode+17.5points ahead
Where EXAONE 4.5 33B pulls ahead
- Math problems shown in pictures and chartsMathVista+5.7points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.1points ahead
- US invitational high-school math exam problemsAIME 2026+3.4points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 31B
- Terminal-Bench 2.1Gemma 4 31B by 22.121.343.4+22.1
- SciCodeGemma 4 31B by 17.52845.5+17.5
- Terminal-Bench HardGemma 4 31B by 15.920.536.4+15.9
- LiveCodeBench v6EXAONE 4.5 33B by 1.481.480+1.4
AgentsGemma 4 31B
- GDPValGemma 4 31B by 6.106.1+6.1
- τ-Bench V3 · BankingGemma 4 31B by 3.711.114.8+3.7
ReasoningGemma 4 31B
- Humanity's Last ExamGemma 4 31B by 10.712.923.6+10.7
- GPQA DiamondGemma 4 31B by 6.379.485.7+6.3
- CritPtGemma 4 31B by 1.10.31.4+1.1
FactsEven
- AA-Omniscience · Non-hallucinationEXAONE 4.5 33B by 5.120.115+5.1
- AA-Omniscience · AccuracyGemma 4 31B by 3.816.220+3.8
Images and chartsGemma 4 31B
Following instructionsGemma 4 31B
- IFBenchGemma 4 31B by 17.65875.6+17.6
Other results7 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.
- Artificial Analysis Coding IndexGemma 4 31B by 19.823.643.4+19.8
- τ²-Bench Telecom (AA run)EXAONE 4.5 33B by 18.278.159.9+18.2
- AA Agentic IndexEXAONE 4.5 33B by 39.76.7+3
- AA-OmniscienceGemma 4 31B by 2.8-50.7-47.9+2.8
- MMLU-ProGemma 4 31B by 1.983.385.2+1.9
- AA IntelligenceGemma 4 31B by 1.513.214.7+1.5
- AI2Dtie8989tie
Questions people ask
Which is better, EXAONE 4.5 33B or Gemma 4 31B?
Gemma 4 31B wins six of the eight areas we test: coding, agents, reasoning, images and charts, long documents and following instructions. EXAONE 4.5 33B wins math. They are level on facts.
Which is better for coding?
Gemma 4 31B. It wins 3 of the 4 coding tests both models report; EXAONE 4.5 33B wins 1.
How do you compare the two?
We use the 24 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 7 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.