Compare / Command A vs Gemma 3 4B

Command A vs Gemma 3 4B

Which is cheaper, which is more capable, and which does better at each kind of work, from 26 results on 5 sources that measured both models.

CohereCommand A Released 20 May 2026 · $2.50 in · $10.00 out
GoogleGemma 3 4B Released 11 Mar 2025 · $0.040 in · $0.050 out
Command A wins 202 too close to callGemma 3 4B wins 4

Of the 26 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).

Command A or Gemma 3 4B? The short answer

Pick Command A if quality matters most: it scores higher (Intelligence Index 7.0 against 4.8). Pick Gemma 3 4B if cost matters more: it costs 103 times less per token.

  • Gemma 3 4B is cheaper: $0.042 against $4.38 per million tokens, 103 times less.
  • Command A scores higher on the Artificial Analysis Intelligence Index: 7.0 against 4.8.
  • Command A is newer: released 20 May 2026, against 11 Mar 2025 for Gemma 3 4B.
  • On third-party benchmarks, on the results both models have: Command A does better for agents and tool use, reasoning and knowledge and writing; Gemma 3 4B for sticking to the facts.

Head to head

7.0
Intelligence Index
4.8
$4.38
Price per million tokens, blendedlower is better
$0.042
256,000
Context window, tokens
131,072

Every fact side by side

Command AGemma 3 4B
Price per million tokens$2.50 in · $10.00 out$0.040 in · $0.050 out
Blended (3 in : 1 out)$4.38$0.042
Cheapest host, blended–$0.042 (Parasail, BF16)
Intelligence Index7.04.8
Spring Prompt overall––
Output speed, tokens a second59–
Context window256,000 tokens131,072 tokens
Released20 May 2026 (newer)11 Mar 2025
WeightsOpenOpen
Developer based inCanadathe 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 63 of 159 158 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 161 of 187 181 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 117 of 169 157 of 169
Sticking to the factsSummarising without inventing things, and factual answers 106 of 139 32 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.

MeasureCommand AGemma 3 4B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 184 · 255 of 387 measured 1,354 1,303
Business, management and finance · TextArena rating, higher is better 185 · 208 of 380 measured 1,351 1,330
Creative writing · TextArena rating, higher is better 171 · 243 of 385 measured 1,336 1,275
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 218 · 246 of 249 measured 7.0 4.8
GPQA Diamond% of questions, higher is better 196 · 227 of 232 measured 52.7% 29.1%
Humanity's Last Exam% of questions, higher is better 226 · 194 of 250 measured 4.0% 5.3%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 3 results
Overall accuracy · BFCL% correct, higher is better 27 · 74 of 81 measured 46.5%bfcl fc 19.6%bfcl prompt
Irrelevance detection · BFCL% correct, higher is better 32 · 71 of 81 measured 84.2%bfcl fc 53.9%bfcl prompt
Memory · BFCL% correct, higher is better 39 · 53 of 81 measured 16.6%bfcl fc 8.6%bfcl prompt
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 109 · 185 of 230 measured 40.6 24.0
Requested-length error · UGI% off the requested word count, lower is better 124 · 33 of 230 measured 21.0% 9.0%
Style adherence · UGIscore from 0 to 1, higher is better 113 · 214 of 230 measured 0.35 0.29
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 47 · 28 of 104 measured 9.3% 6.4%
Answer rate · Vectara% of documents, higher is better 80 · 103 of 104 measured 97.6% 67.3%
Show all 26 results (12 more)
MeasureCommand AGemma 3 4B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 199 · 270 of 338 measured 1,343 1,260
Instruction following · TextArena rating, higher is better 187 · 270 of 387 measured 1,342 1,267
Writing, literature and language · TextArena rating, higher is better 169 · 237 of 386 measured 1,348 1,298
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 153 · 187 of 195 measured 36.5% 28.3%
Long-context reasoning (AA-LCR)% of questions, higher is better 205 · 226 of 241 measured 21.3% 6.7%
Terminal-Bench Hard% of tasks, higher is better 180 · 180 of 190 measured 0.8% 0.8%
τ²-bench telecom% of tasks, higher is better 178 · 187 of 193 measured 15.2% 5.0%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 5 results
Multi-turn tasks · BFCL% correct, higher is better 35 · 75 of 81 measured 29.5%bfcl fc 0.4%bfcl prompt
Relevance detection · BFCL% correct, higher is better 36 · 1 of 81 measured 81.3%bfcl fc 100.0%bfcl prompt
Single-turn calls (curated) · BFCL% correct, higher is better 22 · 74 of 81 measured 87.6%bfcl fc 61.1%bfcl prompt
Single-turn calls (user-contributed) · BFCL% correct, higher is better 19 · 64 of 81 measured 78.5%bfcl fc 60.8%bfcl prompt
Web search · BFCL% correct, higher is better 21 · 56 of 81 measured 46.5%bfcl fc 1.0%bfcl prompt

Quick answers

Is Command A better than Gemma 3 4B?

Pick Command A if quality matters most: it scores higher (Intelligence Index 7.0 against 4.8). Pick Gemma 3 4B if cost matters more: it costs 103 times less per token.

Which is cheaper, Command A or Gemma 3 4B?

Gemma 3 4B is cheaper: $0.042 against $4.38 per million tokens, 103 times less.

Which is better for agents and tool use, Command A or Gemma 3 4B?

Command A ranks 63 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 158 for Gemma 3 4B.

Which is better for reasoning and knowledge, Command A or Gemma 3 4B?

Command A ranks 161 of 187 models on sale for hard questions across science, maths and general knowledge, against 181 for Gemma 3 4B.

Which is better for writing, Command A or Gemma 3 4B?

Command A ranks 117 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 157 for Gemma 3 4B.

Which is better for sticking to the facts, Command A or Gemma 3 4B?

Gemma 3 4B ranks 32 of 139 models on sale for summarising without inventing things, and factual answers, against 106 for Command A.

Which has the bigger context window, Command A or Gemma 3 4B?

Command A: 256,000 tokens, against 131,072 for Gemma 3 4B.

Run Command A and Gemma 3 4B 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.