Compare / Gemma 4 31B vs Granite 4.2 8B

Gemma 4 31B vs Granite 4.2 8B

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 2 sources that measured both models.

GoogleGemma 4 31B Released 2 Apr 2026 · $0.15 in · $0.40 out
IBMGranite 4.2 8B Released 25 Aug 2026 · $0.060 in · $0.15 out
Gemma 4 31B wins 161 too close to callGranite 4.2 8B wins 1

Of the 18 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).

Gemma 4 31B or Granite 4.2 8B? The short answer

Pick Gemma 4 31B if quality matters most: it scores higher (Intelligence Index 14.7 against 11.1). Pick Granite 4.2 8B if cost matters more: it costs 2.6 times less per token. Granite 4.2 8B is also faster.

  • Granite 4.2 8B is cheaper: $0.082 against $0.21 per million tokens, 2.6 times less.
  • Gemma 4 31B scores higher on the Artificial Analysis Intelligence Index: 14.7 against 11.1.
  • Granite 4.2 8B writes faster: 65 tokens a second against 48.
  • Granite 4.2 8B is newer: released 25 Aug 2026, against 2 Apr 2026 for Gemma 4 31B.
  • On third-party benchmarks, on the results both models have: Gemma 4 31B does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

14.7
Intelligence Index
11.1
$0.21
Price per million tokens, blendedlower is better
$0.082
48
Output speed, tokens a second
65
262,144
Context window, tokens
131,072

Every fact side by side

Gemma 4 31BGranite 4.2 8B
Price per million tokens$0.15 in · $0.40 out$0.060 in · $0.15 out
Blended (3 in : 1 out)$0.21$0.082
Cheapest host, blended$0.16 (CoreWeave, FP4)$0.082 (CoreWeave, BF16)
Intelligence Index14.711.1
Spring Prompt overall––
Output speed, tokens a second4865
Context window262,144 tokens131,072 tokens
Released2 Apr 202625 Aug 2026 (newer)
WeightsOpenOpen
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 106 of 159 126 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 99 of 187 138 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 72 of 169 158 of 169
Sticking to the factsSummarising without inventing things, and factual answers 85 of 139 137 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.

MeasureGemma 4 31BGranite 4.2 8B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 65 · 265 of 387 measured 1,453 1,288
Overall · Text factualityArena rating, higher is better 60 · 158 of 163 measured 1,450 1,342
Business, management and finance · TextArena rating, higher is better 66 · 255 of 380 measured 1,449 1,290
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 136 · 168 of 249 measured 14.7 11.1
GPQA Diamond% of questions, higher is better 76 · 176 of 232 measured 85.7% 63.1%
Humanity's Last Exam% of questions, higher is better 105 · 166 of 250 measured 23.6% 9.7%
Show all 18 results (12 more)
MeasureGemma 4 31BGranite 4.2 8B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 74 · 298 of 385 measured 1,420 1,197
Expert prompts · TextArena rating, higher is better 42 · 179 of 338 measured 1,498 1,371
Instruction following · TextArena rating, higher is better 49 · 258 of 387 measured 1,453 1,281
Writing, literature and language · TextArena rating, higher is better 63 · 288 of 386 measured 1,435 1,237
Artificial Analysis reported by Artificial Analysis · 8 results
Terminal-Bench 2.1% of tasks, higher is better 72 · 94 of 131 measured 43.4% 18.4%
Terminal-Bench 4.0% of tasks, higher is better 72 · 72 of 120 measured 0.0% 0.0%
τ-bench banking% of tasks, higher is better 61 · 88 of 121 measured 14.8% 7.6%
Artificial Analysis Coding Indexindex score, higher is better 69 · 96 of 130 measured 43.4 22.4
Long-context reasoning (AA-LCR)% of questions, higher is better 119 · 170 of 241 measured 69.7% 45.0%
Output speedtokens per second, higher is better 68 · 60 of 78 measured 47.6no reasoning 64.9
SciCode% of problems, higher is better 72 · 107 of 121 measured 45.5% 31.5%
Time to first answer tokenseconds, lower is better 22 · 67 of 78 measured 0.77no reasoning 31.2

Quick answers

Is Gemma 4 31B better than Granite 4.2 8B?

Pick Gemma 4 31B if quality matters most: it scores higher (Intelligence Index 14.7 against 11.1). Pick Granite 4.2 8B if cost matters more: it costs 2.6 times less per token. Granite 4.2 8B is also faster.

Which is cheaper, Gemma 4 31B or Granite 4.2 8B?

Granite 4.2 8B is cheaper: $0.082 against $0.21 per million tokens, 2.6 times less.

Which is faster, Gemma 4 31B or Granite 4.2 8B?

Granite 4.2 8B writes about 65 tokens a second on its usual API, against 48 for Gemma 4 31B (Artificial Analysis).

Which is better for agents and tool use, Gemma 4 31B or Granite 4.2 8B?

Gemma 4 31B ranks 106 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 126 for Granite 4.2 8B.

Which is better for reasoning and knowledge, Gemma 4 31B or Granite 4.2 8B?

Gemma 4 31B ranks 99 of 187 models on sale for hard questions across science, maths and general knowledge, against 138 for Granite 4.2 8B.

Which is better for writing, Gemma 4 31B or Granite 4.2 8B?

Gemma 4 31B ranks 72 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 158 for Granite 4.2 8B.

Which is better for sticking to the facts, Gemma 4 31B or Granite 4.2 8B?

Gemma 4 31B ranks 85 of 139 models on sale for summarising without inventing things, and factual answers, against 137 for Granite 4.2 8B.

Which has the bigger context window, Gemma 4 31B or Granite 4.2 8B?

Gemma 4 31B: 262,144 tokens, against 131,072 for Granite 4.2 8B.

Run Gemma 4 31B and Granite 4.2 8B 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.