Gemini 2.5 Pro vs Gemma 4 26B A4B
Wins 4 of 7 areas
Coding · Reasoning · Images and charts · Long documents
Wins 3 of 7 areas
Agents · Facts · Following instructions
Gemini 2.5 Pro wins more areas, narrowly.Gemma 4 26B A4B is cheaper and better at agents.
Scores updated · 34 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 video30Gemini 2.5 Pro3 of 4 tests · 1 tie
- CodingWriting and fixing software32Gemini 2.5 Pro3 of 5 tests
- ReasoningHard problems that need careful thinking21Gemini 2.5 Pro2 of 3 tests
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own03Gemma 4 26B A4B3 of 3 tests
- FactsGetting facts right instead of making them up12Gemma 4 26B A4B2 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemma 4 26B A4B1 of 1 test
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.
Gemma 4 26B A4B costs 95% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 2.5 Pro pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+45.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+20points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+12.9points ahead
Where Gemma 4 26B A4B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+23.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+16.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+10.5points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- SWE-bench VerifiedGemini 2.5 Pro by 45.863.217.4+45.8
- LMArena · WebDevGemma 4 26B A4B by 135 rating points12241359+135 rating
- Terminal-Bench HardGemini 2.5 Pro by 12.926.513.6+12.9
- Terminal-Bench 2.1Gemma 4 26B A4B by 10.528.539+10.5
- SciCodeGemini 2.5 Pro by 6.346.340+6.3
AgentsGemma 4 26B A4B
- BrowseCompGemma 4 26B A4B by 16.49.926.3+16.4
- GDPValGemma 4 26B A4B by 3.403.4+3.4
- τ-Bench V3 · BankingGemma 4 26B A4B by 2.39.712+2.3
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 4.483.679.2+4.4
- CritPtGemini 2.5 Pro by 2.62.60+2.6
- Humanity's Last ExamGemma 4 26B A4B by 1.31819.3+1.3
FactsGemma 4 26B A4B
- AA-Omniscience · AccuracyGemini 2.5 Pro by 203919.1+20
- AA-Omniscience · Non-hallucinationGemma 4 26B A4B by 4.59.113.6+4.5
- Vectara HHEM hallucination ratelower is betterGemma 4 26B A4B by 1.875.2+1.8
Images and chartsGemini 2.5 Pro
- MMMU-ProGemini 2.5 Pro by 5.774.969.2+5.7
- MathVistaGemini 2.5 Pro by 4.583.979.4+4.5
- MMMUGemini 2.5 Pro by 1.279.678.4+1.2
- LMArena · Visiontie12631260tie
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 23.748.772.4+23.7
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-OmniscienceGemini 2.5 Pro by 34.5-16.4-50.8+34.5
- τ²-BenchGemma 4 26B A4B by 14.25468.2+14.2
- HLE (with tools)Gemini 2.5 Pro by 11.228.417.2+11.2
- HMMT Feb. 2025Gemma 4 26B A4B by 10.980.891.7+10.9
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 10.554.143.6+10.5
- MATH-VisionGemma 4 26B A4B by 9.173.382.4+9.1
- AA Agentic IndexGemma 4 26B A4B by 7.53.511+7.5
- HMMT Nov. 2025Gemma 4 26B A4B by 7.58087.5+7.5
- Artificial Analysis Coding IndexGemini 2.5 Pro by 7.446.739.3+7.4
- vectara_avg_summary_lengthGemini 2.5 Pro by 39.3 rating points106.467.1+39.3 rating
- MMLU-ProGemini 2.5 Pro by 3.48682.6+3.4
- vectara_factual_consistencyGemma 4 26B A4B by 1.89394.8+1.8
- AA IntelligenceGemma 4 26B A4B by 1.71516.7+1.7
- vectara_answer_ratetie99.199.8tie
Questions people ask
Which is better, Gemini 2.5 Pro or Gemma 4 26B A4B?
Gemini 2.5 Pro wins four of the seven areas where both have results: coding, reasoning, images and charts and long documents. Gemma 4 26B A4B wins agents, facts and following instructions, and costs 95% less.
Which is better for coding?
Gemini 2.5 Pro. It wins 3 of the 5 coding tests both models report; Gemma 4 26B A4B wins 2.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Gemma 4 26B A4B costs $0.13 and $0.40. That makes Gemma 4 26B A4B about 95% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 20 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.