Compare / Claude Sonnet 4 vs Gemma 4 26B A4B

Claude Sonnet 4 vs Gemma 4 26B A4B

Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 4 sources that measured both models.

AnthropicClaude Sonnet 4 Released 22 May 2025 · Not on sale
GoogleGemma 4 26B A4B Released 2 Apr 2026 · $0.090 in · $0.30 out
Claude Sonnet 4 wins 82 too close to callGemma 4 26B A4B wins 11

Of the 21 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Anthropic vs Google, every model from both labs.

Claude Sonnet 4 or Gemma 4 26B A4B? The short answer

Pick Claude Sonnet 4: it scores higher (Intelligence Index 18.9 against 16.7) at about the same price.

  • Claude Sonnet 4 scores higher on the Artificial Analysis Intelligence Index: 18.9 against 16.7.
  • Gemma 4 26B A4B is newer: released 2 Apr 2026, against 22 May 2025 for Claude Sonnet 4.
  • On third-party benchmarks, on the results both models have: Gemma 4 26B A4B does better for reasoning and knowledge and sticking to the facts.

Head to head

18.9
Intelligence Index
16.7

Every fact side by side

Claude Sonnet 4Gemma 4 26B A4B
Price per million tokensNot on sale$0.090 in · $0.30 out
Blended (3 in : 1 out)–$0.14
Cheapest host, blended–$0.068 (Darkbloom)
Intelligence Index18.916.7
Spring Prompt overall––
Output speed, tokens a second–82
Context window–262,144 tokens
Released22 May 20252 Apr 2026 (newer)
WeightsClosedOpen
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 93 of 160 105 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 118 of 188 110 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 68 of 170 82 of 169
Sticking to the factsSummarising without inventing things, and factual answers 82 of 140 43 of 139

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureClaude Sonnet 4Gemma 4 26B A4B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 136 · 87 of 387 measured 1,402thinking-32k reasoning 1,437
Business, management and finance · TextArena rating, higher is better 153 · 78 of 380 measured 1,387 1,444
Creative writing · TextArena rating, higher is better 98 · 96 of 385 measured 1,396thinking-32k reasoning 1,400
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 115 · 123 of 249 measured 18.9thinking reasoning 16.7
GPQA Diamond% of questions, higher is better 123 · 113 of 232 measured 77.7%thinking reasoning 79.2%
Humanity's Last Exam% of questions, higher is better 156 · 119 of 250 measured 10.7%thinking reasoning 19.3%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 32 · 92 of 230 measured 63.7no reasoning 43.8channel-thought-prefill reasoning
Requested-length error · UGI% off the requested word count, lower is better 13 · 25 of 230 measured 4.0%no reasoning 8.0%
Style adherence · UGIscore from 0 to 1, higher is better 76 · 93 of 230 measured 0.36no reasoning 0.35channel-thought-prefill reasoning
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 60 · 13 of 104 measured 10.3% 5.2%
Answer rate · Vectara% of documents, higher is better 72 · 31 of 104 measured 98.6% 99.8%
Show all 21 results (10 more)
MeasureClaude Sonnet 4Gemma 4 26B A4B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 120 · 71 of 338 measured 1,433thinking-32k reasoning 1,475
Instruction following · TextArena rating, higher is better 100 · 71 of 387 measured 1,415thinking-32k reasoning 1,437
Writing, literature and language · TextArena rating, higher is better 111 · 97 of 386 measured 1,398thinking-32k reasoning 1,406
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 78 · 75 of 131 measured 36.3%thinking reasoning 39.0%
τ-bench banking% of tasks, higher is better 54 · 70 of 121 measured 16.7%thinking reasoning 12.0%
Artificial Analysis Coding Indexindex score, higher is better 77 · 74 of 130 measured 37.6thinking reasoning 39.3
IFBench% of instructions, higher is better 91 · 40 of 195 measured 54.7%thinking reasoning 72.4%
Long-context reasoning (AA-LCR)% of questions, higher is better 114 · 131 of 241 measured 70.3%thinking reasoning 65.7%
Terminal-Bench Hard% of tasks, higher is better 65 · 78 of 190 measured 31.1%thinking reasoning 25.0%no reasoning
τ²-bench telecom% of tasks, higher is better 90 · 110 of 193 measured 64.6%thinking reasoning 43.6%

Quick answers

Is Claude Sonnet 4 better than Gemma 4 26B A4B?

Pick Claude Sonnet 4: it scores higher (Intelligence Index 18.9 against 16.7) at about the same price.

Which is better for agents and tool use, Claude Sonnet 4 or Gemma 4 26B A4B?

Claude Sonnet 4 ranks 93 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 105 for Gemma 4 26B A4B.

Which is better for reasoning and knowledge, Claude Sonnet 4 or Gemma 4 26B A4B?

Gemma 4 26B A4B ranks 110 of 188 models on sale for hard questions across science, maths and general knowledge, against 118 for Claude Sonnet 4.

Which is better for writing, Claude Sonnet 4 or Gemma 4 26B A4B?

Claude Sonnet 4 ranks 68 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 82 for Gemma 4 26B A4B.

Which is better for sticking to the facts, Claude Sonnet 4 or Gemma 4 26B A4B?

Gemma 4 26B A4B ranks 43 of 140 models on sale for summarising without inventing things, and factual answers, against 82 for Claude Sonnet 4.

Run Claude Sonnet 4 and Gemma 4 26B A4B on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.