Claude Sonnet 4.6 vs Gemma 4 31B
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 31B 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
- FactsGetting facts right instead of making them up31Claude Sonnet 4.63 of 4 tests
- Long documentsFinding answers in very long texts20Claude Sonnet 4.62 of 2 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Sonnet 4.61 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked01Gemma 4 31B1 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 31B 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
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36.6points ahead
- Real work tasks from 44 professionsGDPVal+30.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+27.8points ahead
Where Gemma 4 31B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+19points 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
- Terminal-Bench 2.1Claude Sonnet 4.6 by 27.871.243.4+27.8
- SWE-bench VerifiedClaude Sonnet 4.6 by 27.679.652+27.6
- SWE-bench ProClaude Sonnet 4.6 by 22.458.135.7+22.4
- Terminal-Bench HardClaude Sonnet 4.6 by 16.65336.4+16.6
- LMArena · WebDevClaude Sonnet 4.6 by 157 rating points15221365+157 rating
- SciCodeClaude Sonnet 4.6 by 4.650.145.5+4.6
AgentsClaude Sonnet 4.6
- GDPValClaude Sonnet 4.6 by 30.636.76.1+30.6
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 19.634.414.8+19.6
- MCP AtlasClaude Sonnet 4.6 by 4.161.357.2+4.1
- Terminal-Bench 4.0Claude Sonnet 4.6 by 330+3
- AA IT-Bench SREClaude Sonnet 4.6 by 2.539.837.3+2.5
ReasoningClaude Sonnet 4.6
- Humanity's Last ExamClaude Sonnet 4.6 by 1033.623.6+10
- GPQA DiamondClaude Sonnet 4.6 by 1.887.585.7+1.8
- CritPtClaude Sonnet 4.6 by 1.73.11.4+1.7
FactsClaude Sonnet 4.6
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 36.651.615+36.6
- SimpleQA VerifiedClaude Sonnet 4.6 by 22.432.810.4+22.4
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 20.940.920+20.9
- Vectara HHEM hallucination ratelower is betterGemma 4 31B by 3.210.67.4+3.2
Images and chartsClaude Sonnet 4.6
- CharXiv (RQ)Claude Sonnet 4.6 by 3.771.667.9+3.7
- LMArena · Visiontie12831277tie
- MMMU-Protie73.373.4tie
Long documentsClaude Sonnet 4.6
- MRCR v2 8 needle 128k (average)Claude Sonnet 4.6 by 18.584.966.4+18.5
- AA-LCRClaude Sonnet 4.6 by 10.38069.7+10.3
Following instructionsGemma 4 31B
- IFBenchGemma 4 31B by 1956.675.6+19
Other results12 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 60.112.2-47.9+60.1
- AA Agentic IndexClaude Sonnet 4.6 by 26.433.16.7+26.4
- HLE (with tools)Claude Sonnet 4.6 by 20.346.826.5+20.3
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 19.66343.4+19.6
- Terminal-Bench 2.0Claude Sonnet 4.6 by 16.259.142.9+16.2
- τ²-Bench Telecom (AA run)Claude Sonnet 4.6 by 15.875.759.9+15.8
- AA IntelligenceClaude Sonnet 4.6 by 15.430.114.7+15.4
- GPQA (unspecified)Claude Sonnet 4.6 by 5.689.984.3+5.6
- vectara_avg_summary_lengthClaude Sonnet 4.6 by 38.9 rating points114.775.8+38.9 rating
- vectara_factual_consistencyGemma 4 31B by 3.289.492.6+3.2
- MMMLUtie89.388.4tie
- vectara_answer_ratetie99.9100tie
Questions people ask
Which is better, Claude Sonnet 4.6 or Gemma 4 31B?
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 31B 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 31B 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 31B costs $0.17 and $0.40. That makes Gemma 4 31B 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 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.