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.
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
Every fact side by side
| Gemma 4 31B | Granite 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 Index | 14.7 | 11.1 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 48 | 65 |
| Context window | 262,144 tokens | 131,072 tokens |
| Released | 2 Apr 2026 | 25 Aug 2026 (newer) |
| Weights | Open | Open |
| Developer based in | the US | the 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.
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.
| Measure | Gemma 4 31B | Granite 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)
| Measure | Gemma 4 31B | Granite 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.