Compare / Qwen3.7-Max vs Gemma 4 31B

Qwen3.7-Max vs Gemma 4 31B

Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 2 sources that measured both models.

AlibabaQwen3.7-Max Released 19 May 2026 · $1.48 in · $4.42 out
GoogleGemma 4 31B Released 2 Apr 2026 · $0.14 in · $0.40 out
Qwen3.7-Max wins 12Gemma 4 31B wins 1

Of the 13 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 13 October 2026 (catalogue release 2026-10-13-2e2420e3c5cc). See also Alibaba vs Google, every model from both labs.

Qwen3.7-Max or Gemma 4 31B? The short answer

Pick Qwen3.7-Max if quality matters most: it scores higher (Intelligence Index 29.5 against 14.7). Pick Gemma 4 31B if cost matters more: it costs 11 times less per token.

  • Gemma 4 31B is cheaper: $0.21 against $2.21 per million tokens, 11 times less.
  • Qwen3.7-Max scores higher on the Artificial Analysis Intelligence Index: 29.5 against 14.7.
  • Qwen3.7-Max is newer: released 19 May 2026, against 2 Apr 2026 for Gemma 4 31B.
  • On third-party benchmarks, on the results both models have: Qwen3.7-Max does better for agents and tool use, reasoning and knowledge and sticking to the facts.

Head to head

29.5
Intelligence Index
14.7
$2.21
Price per million tokens, blendedlower is better
$0.21
1,000,000
Context window, tokens
262,144

Every fact side by side

Qwen3.7-MaxGemma 4 31B
Price per million tokens$1.48 in · $4.42 out$0.14 in · $0.40 out
Blended (3 in : 1 out)$2.21$0.21
Cheapest host, blended–$0.15 (DeepInfra, FP4)
Intelligence Index29.514.7
Spring Prompt overall––
Output speed, tokens a second–43
Context window1,000,000 tokens262,144 tokens
Released19 May 2026 (newer)2 Apr 2026
WeightsClosedOpen
Developer based inChinathe 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 69 of 164 101 of 164
Reasoning and knowledgeHard questions across science, maths and general knowledge 39 of 198 93 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality not measured 74 of 188
Sticking to the factsSummarising without inventing things, and factual answers 31 of 152 90 of 152

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.

MeasureQwen3.7-MaxGemma 4 31B
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 53 · 130 of 243 measured 29.5 14.7
GPQA Diamond% of questions, higher is better 21 · 75 of 231 measured 92.3% 85.7%
Humanity's Last Exam% of questions, higher is better 39 · 97 of 242 measured 40.5% 23.6%
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 18 · 74 of 76 measured 55.8% 10.4%
Show all 13 results (9 more)
MeasureQwen3.7-MaxGemma 4 31B
Artificial Analysis reported by Artificial Analysis · 9 results
Terminal-Bench 2.1% of tasks, higher is better 33 · 71 of 130 measured 74.5% 43.4%
Terminal-Bench 4.0% of tasks, higher is better 51 · 66 of 112 measured 1.5% 0.0%
τ-bench banking% of tasks, higher is better 71 · 61 of 121 measured 11.8% 14.8%
Artificial Analysis Coding Indexindex score, higher is better 34 · 70 of 131 measured 66.0 43.4
IFBench% of instructions, higher is better 5 · 24 of 195 measured 80.5% 75.6%
Long-context reasoning (AA-LCR)% of questions, higher is better 50 · 112 of 233 measured 79.0% 69.7%
SciCode% of problems, higher is better 52 · 63 of 113 measured 49.5% 45.5%
Terminal-Bench Hard% of tasks, higher is better 12 · 46 of 190 measured 50.8% 36.4%
τ²-bench telecom% of tasks, higher is better 22 · 88 of 193 measured 94.7% 65.5%no reasoning

Quick answers

Is Qwen3.7-Max better than Gemma 4 31B?

Pick Qwen3.7-Max if quality matters most: it scores higher (Intelligence Index 29.5 against 14.7). Pick Gemma 4 31B if cost matters more: it costs 11 times less per token.

Which is cheaper, Qwen3.7-Max or Gemma 4 31B?

Gemma 4 31B is cheaper: $0.21 against $2.21 per million tokens, 11 times less.

Which is better for agents and tool use, Qwen3.7-Max or Gemma 4 31B?

Qwen3.7-Max ranks 69 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 101 for Gemma 4 31B.

Which is better for reasoning and knowledge, Qwen3.7-Max or Gemma 4 31B?

Qwen3.7-Max ranks 39 of 198 models on sale for hard questions across science, maths and general knowledge, against 93 for Gemma 4 31B.

Which is better for sticking to the facts, Qwen3.7-Max or Gemma 4 31B?

Qwen3.7-Max ranks 31 of 152 models on sale for summarising without inventing things, and factual answers, against 90 for Gemma 4 31B.

Which has the bigger context window, Qwen3.7-Max or Gemma 4 31B?

Qwen3.7-Max: 1,000,000 tokens, against 262,144 for Gemma 4 31B.

Run Qwen3.7-Max and Gemma 4 31B on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.

Try the playgroundTalk to us