Claude Sonnet 4 vs Gemma 4 26B A4B
Wins 4 of 7 areas
Coding · Agents · Facts · Long documents
Wins 3 of 7 areas
Reasoning · Images and charts · Following instructions
Claude Sonnet 4 wins more areas, narrowly.Gemma 4 26B A4B is cheaper and better at images and charts.
Scores updated · 37 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.
- CodingWriting and fixing software42Claude Sonnet 44 of 7 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own21Claude Sonnet 42 of 3 tests
- FactsGetting facts right instead of making them up21Claude Sonnet 42 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- Images and chartsUnderstanding pictures, charts and video03Gemma 4 26B A4B3 of 3 tests
- ReasoningHard problems that need careful thinking02Gemma 4 26B A4B2 of 3 tests · 1 tie
- 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 97% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+57.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+55.3points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+39.6points ahead
Where Gemma 4 26B A4B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+28.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+14.1points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- SWE-bench VerifiedClaude Sonnet 4 by 55.372.717.4+55.3
- SWE-bench MultilingualClaude Sonnet 4 by 39.656.917.3+39.6
- SWE-bench ProClaude Sonnet 4 by 28.942.713.8+28.9
- LiveCodeBench v6Gemma 4 26B A4B by 28.648.577.1+28.6
- Terminal-Bench HardClaude Sonnet 4 by 17.531.113.6+17.5
- Terminal-Bench 2.1Gemma 4 26B A4B by 2.736.339+2.7
- SciCodetie4040tie
AgentsClaude Sonnet 4
- BrowseCompGemma 4 26B A4B by 14.112.226.3+14.1
- GDPValClaude Sonnet 4 by 6.39.73.4+6.3
- τ-Bench V3 · BankingClaude Sonnet 4 by 4.716.712+4.7
ReasoningGemma 4 26B A4B
- Humanity's Last ExamGemma 4 26B A4B by 8.610.719.3+8.6
- GPQA DiamondGemma 4 26B A4B by 1.577.779.2+1.5
- CritPttie0.30tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 57.370.913.6+57.3
- Vectara HHEM hallucination ratelower is betterGemma 4 26B A4B by 5.110.35.2+5.1
- AA-Omniscience · AccuracyClaude Sonnet 4 by 3.622.719.1+3.6
Images and chartsGemma 4 26B A4B
- MMMU-ProGemma 4 26B A4B by 7.461.869.2+7.4
- LMArena · VisionGemma 4 26B A4B by 69 rating points11911260+69 rating
- MMMUGemma 4 26B A4B by 474.478.4+4
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 17.754.772.4+17.7
Other results16 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-OmniscienceClaude Sonnet 4 by 510.2-50.8+51
- τ²-BenchGemma 4 26B A4B by 2345.268.2+23
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 2164.643.6+21
- MMLUClaude Sonnet 4 by 13.791.577.8+13.7
- vectara_avg_summary_lengthClaude Sonnet 4 by 78.7 rating points145.867.1+78.7 rating
- AA Agentic IndexClaude Sonnet 4 by 6.617.611+6.6
- SuperGPQAGemma 4 26B A4B by 5.755.761.4+5.7
- vectara_factual_consistencyGemma 4 26B A4B by 5.189.794.8+5.1
- IFEvalGemma 4 26B A4B by 3.887.691.4+3.8
- HLE (with tools)Claude Sonnet 4 by 3.120.317.2+3.1
- AA IntelligenceClaude Sonnet 4 by 2.218.916.7+2.2
- Artificial Analysis Coding IndexGemma 4 26B A4B by 1.737.639.3+1.7
- vectara_answer_rateGemma 4 26B A4B by 1.298.699.8+1.2
- MMLU-ProClaude Sonnet 4 by 1.183.782.6+1.1
- MMLU-Reduxtie93.692.7tie
- MMMLUtie86.586.3tie
Questions people ask
Which is better, Claude Sonnet 4 or Gemma 4 26B A4B?
Claude Sonnet 4 wins four of the seven areas where both have results: coding, agents, facts and long documents. Gemma 4 26B A4B wins reasoning, images and charts and following instructions, and costs 97% less.
Which is better for coding?
Claude Sonnet 4. It wins 4 of the 7 coding tests both models report; Gemma 4 26B A4B wins 2, and 1 is a tie.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemma 4 26B A4B costs $0.13 and $0.40. That makes Gemma 4 26B A4B about 97% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.