Claude Sonnet 4.6 vs Gemma 4 26B A4B
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Wins 1 of 7 areas
Following instructions
Claude Sonnet 4.6 is the stronger all-rounder.Gemma 4 26B A4B is cheaper and better at following instructions.
Scores updated · 36 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 software60Claude Sonnet 4.66 of 6 tests
- AgentsCarrying out multi-step tasks on its own50Claude Sonnet 4.65 of 5 tests
- ReasoningHard problems that need careful thinking30Claude Sonnet 4.63 of 3 tests
- Images and chartsUnderstanding pictures, charts and video30Claude Sonnet 4.63 of 3 tests
- Long documentsFinding answers in very long texts20Claude Sonnet 4.62 of 2 tests
- FactsGetting facts right instead of making them up21Claude Sonnet 4.62 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemma 4 26B A4B1 of 1 test
Following instructions rests on a single test.
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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Sonnet 4.6 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+62.2points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+48.4points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+44.3points ahead
Where Gemma 4 26B A4B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.8points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.6
- SWE-bench VerifiedClaude Sonnet 4.6 by 62.279.617.4+62.2
- SWE-bench ProClaude Sonnet 4.6 by 44.358.113.8+44.3
- Terminal-Bench HardClaude Sonnet 4.6 by 39.45313.6+39.4
- Terminal-Bench 2.1Claude Sonnet 4.6 by 32.271.239+32.2
- LMArena · WebDevClaude Sonnet 4.6 by 163 rating points15221359+163 rating
- SciCodeClaude Sonnet 4.6 by 10.150.140+10.1
AgentsClaude Sonnet 4.6
- BrowseCompClaude Sonnet 4.6 by 48.474.726.3+48.4
- GDPValClaude Sonnet 4.6 by 33.336.73.4+33.3
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 22.434.412+22.4
- AA IT-Bench SREClaude Sonnet 4.6 by 16.239.823.6+16.2
- MCP AtlasClaude Sonnet 4.6 by 11.361.350+11.3
ReasoningClaude Sonnet 4.6
- Humanity's Last ExamClaude Sonnet 4.6 by 14.333.619.3+14.3
- GPQA DiamondClaude Sonnet 4.6 by 8.387.579.2+8.3
- CritPtClaude Sonnet 4.6 by 3.13.10+3.1
FactsClaude Sonnet 4.6
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 3851.613.6+38
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 21.840.919.1+21.8
- Vectara HHEM hallucination ratelower is betterGemma 4 26B A4B by 5.410.65.2+5.4
Images and chartsClaude Sonnet 4.6
- MMMU-ProClaude Sonnet 4.6 by 4.173.369.2+4.1
- CharXiv (RQ)Claude Sonnet 4.6 by 2.671.669+2.6
- LMArena · VisionClaude Sonnet 4.6 by 23 rating points12831260+23 rating
Long documentsClaude Sonnet 4.6
- MRCR v2 8 needle 128k (average)Claude Sonnet 4.6 by 40.884.944.1+40.8
- AA-LCRClaude Sonnet 4.6 by 14.38065.7+14.3
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 15.856.672.4+15.8
Other results13 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 4.6 by 6312.2-50.8+63
- GDPval-AA v2Claude Sonnet 4.6 by 588 rating points1395807+588 rating
- τ²-Bench Telecom (AA run)Claude Sonnet 4.6 by 32.175.743.6+32.1
- HLE (with tools)Claude Sonnet 4.6 by 29.646.817.2+29.6
- Terminal-Bench 2.0Claude Sonnet 4.6 by 24.959.134.2+24.9
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 23.76339.3+23.7
- AA Agentic IndexClaude Sonnet 4.6 by 22.133.111+22.1
- AA IntelligenceClaude Sonnet 4.6 by 13.430.116.7+13.4
- GPQA (unspecified)Claude Sonnet 4.6 by 7.689.982.3+7.6
- vectara_factual_consistencyGemma 4 26B A4B by 5.489.494.8+5.4
- vectara_avg_summary_lengthClaude Sonnet 4.6 by 47.6 rating points114.767.1+47.6 rating
- MMMLUClaude Sonnet 4.6 by 389.386.3+3
- vectara_answer_ratetie99.999.8tie
Questions people ask
Which is better, Claude Sonnet 4.6 or Gemma 4 26B A4B?
Claude Sonnet 4.6 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. Gemma 4 26B A4B wins following instructions, and costs 97% less.
Which is better for coding?
Claude Sonnet 4.6. It wins 6 of the 6 coding tests both models report; Gemma 4 26B A4B wins none.
Which is cheaper?
Claude Sonnet 4.6 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 36 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.