Compare / Gemma 4 26B A4B vs MiniMax-M2

Gemma 4 26B A4B vs MiniMax-M2

Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 3 sources that measured both models.

GoogleGemma 4 26B A4B Released 2 Apr 2026 · $0.090 in · $0.30 out
MiniMaxMiniMax-M2 Released 27 Oct 2025 · Not on sale
Gemma 4 26B A4B wins 13MiniMax-M2 wins 4

Of the 17 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331). See also Google vs MiniMax, every model from both labs.

Gemma 4 26B A4B or MiniMax-M2? The short answer

They score and cost about the same: pick on the results below that match your work.

  • MiniMax-M2 scores higher on the Artificial Analysis Intelligence Index: 18.6 against 16.7.
  • Gemma 4 26B A4B is newer: released 2 Apr 2026, against 27 Oct 2025 for MiniMax-M2.
  • On third-party benchmarks, on the results both models have: Gemma 4 26B A4B does better for reasoning and knowledge, writing and sticking to the facts.

Head to head

16.7
Intelligence Index
18.6

Every fact side by side

Gemma 4 26B A4BMiniMax-M2
Price per million tokens$0.090 in · $0.30 outNot on sale
Blended (3 in : 1 out)$0.14–
Cheapest host, blended$0.068 (Darkbloom)–
Intelligence Index16.718.6
Spring Prompt overall––
Output speed, tokens a second82–
Context window262,144 tokens–
Released2 Apr 2026 (newer)27 Oct 2025
WeightsOpenClosed
Developer based inthe USChina

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 105 of 159 150 of 160
Reasoning and knowledgeHard questions across science, maths and general knowledge 110 of 187 116 of 188
WritingWhat people prefer in blind comparisons, and judged writing quality 82 of 169 152 of 170
Sticking to the factsSummarising without inventing things, and factual answers 43 of 139 137 of 140

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.

MeasureGemma 4 26B A4BMiniMax-M2
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 87 · 199 of 387 measured 1,437 1,343
Overall · Text factualityArena rating, higher is better 71 · 156 of 163 measured 1,445 1,360
Business, management and finance · TextArena rating, higher is better 78 · 196 of 380 measured 1,444 1,348
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 123 · 116 of 249 measured 16.7 18.6
GPQA Diamond% of questions, higher is better 113 · 123 of 232 measured 79.2% 77.7%
Humanity's Last Exam% of questions, higher is better 119 · 141 of 250 measured 19.3% 13.7%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 92 · 215 of 230 measured 43.8channel-thought-prefill reasoning 17.2
Requested-length error · UGI% off the requested word count, lower is better 25 · 213 of 230 measured 8.0% 73.0%
Style adherence · UGIscore from 0 to 1, higher is better 93 · 55 of 230 measured 0.35channel-thought-prefill reasoning 0.37
Show all 17 results (8 more)
MeasureGemma 4 26B A4BMiniMax-M2
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 96 · 229 of 385 measured 1,400 1,285
Expert prompts · TextArena rating, higher is better 71 · 194 of 338 measured 1,475 1,350
Instruction following · TextArena rating, higher is better 71 · 193 of 387 measured 1,437 1,334
Writing, literature and language · TextArena rating, higher is better 97 · 232 of 386 measured 1,406 1,299
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 40 · 41 of 195 measured 72.4% 72.3%
Long-context reasoning (AA-LCR)% of questions, higher is better 131 · 138 of 241 measured 65.7% 64.3%
Terminal-Bench Hard% of tasks, higher is better 78 · 77 of 190 measured 25.0%no reasoning 25.8%
τ²-bench telecom% of tasks, higher is better 110 · 51 of 193 measured 43.6% 86.8%

Quick answers

Is Gemma 4 26B A4B better than MiniMax-M2?

They score and cost about the same: pick on the results below that match your work.

Which is better for agents and tool use, Gemma 4 26B A4B or MiniMax-M2?

Gemma 4 26B A4B ranks 105 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 150 for MiniMax-M2.

Which is better for reasoning and knowledge, Gemma 4 26B A4B or MiniMax-M2?

Gemma 4 26B A4B ranks 110 of 187 models on sale for hard questions across science, maths and general knowledge, against 116 for MiniMax-M2.

Which is better for writing, Gemma 4 26B A4B or MiniMax-M2?

Gemma 4 26B A4B ranks 82 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 152 for MiniMax-M2.

Which is better for sticking to the facts, Gemma 4 26B A4B or MiniMax-M2?

Gemma 4 26B A4B ranks 43 of 139 models on sale for summarising without inventing things, and factual answers, against 137 for MiniMax-M2.

Run Gemma 4 26B A4B and MiniMax-M2 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.