Model comparison
Gemma 4 31B IT vs Grok 4.7
Grok 4.7 is the stronger model overall, scoring 53.1 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 20× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Gemma 4 31B IT scores higher in 4 categories and Grok 4.7 in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.7 leads 62.8 to 37.9.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 56% for Grok 4.7.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Grok 4.7 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 43.5 | 53.1 |
| Released | 2026-04-02 | 2026-09-21 |
| Weights | Open | Proprietary |
| Context window | 262K | 500K |
| Max output | 33K | 500K |
| Input $ / M tokens | $0.09 | $2 |
| Output $ / M tokens | $0.34 | $6 |
| Results tracked | 35 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Gemma 4 31B IT: 42.3 (#108), Grok 4.7: 58.0 (#18)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| LMArena WebDev | 1366 | 1639 |
| SciCode | 43.4% | 57.8% |
| LMArena Coding | 1459 | 1427 |
| FrontierCode | — | 47.6% |
| CursorBench | — | 46.3% |
| FrontierSWE | — | 29.5% |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Grok 4.7: 36.7 (#37)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| APEX-Agents | — | 54.6% |
| GDP.pdf | — | 22.8% |
| Vending-Bench 2 | — | 10,537 |
Reasoning Grok 4.7 leads
Gemma 4 31B IT: 27.2 (#122), Grok 4.7: 49.1 (#40)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| NYT Connections (extended) | 70.6% | 76.8% |
| CritPt | 1.4% | 18% |
| Chess Puzzles | 5% | 38% |
| LMArena Hard Prompts | 1448 | 1413 |
| DTBench | 82.7% | 96% |
| LMCA | 39.3% | 49.4% |
| Epoch Capabilities Index | 142.74 | 153.53 |
| Kagi LLM Benchmark | 63.5% | — |
| Thematic Generalization | 53% | — |
| Mystery Game Puzzles | — | 29% |
| Surface Evolver Bench | 30.6% | — |
Math Grok 4.7 leads
Gemma 4 31B IT: 43.2 (#81), Grok 4.7: 57.8 (#39)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 98.1% |
| LMArena Math | 1465 | 1407 |
| FrontierMath (Tiers 1-3) | — | 53% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 34% |
Knowledge Grok 4.7 leads
Gemma 4 31B IT: 37.9 (#151), Grok 4.7: 62.8 (#22)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| GPQA Diamond | 75.8% | 92.7% |
| SimpleQA Verified | 10.4% | 56% |
| LMArena Expert | 1465 | 1422 |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.6 (#34), Grok 4.7: 35.5 (#87)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| LMArena Vision | 1277 | 1228 |
| Blueprint-Bench 2 | — | 32.5% |
| Furniture Assembly | — | 20.8% |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Grok 4.7: 50.8 (#116)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1431 | 1389 |
| LMArena Chinese | 1476 | 1455 |
| LMArena French | 1435 | 1455 |
| LMArena Russian | 1460 | 1397 |
| LMArena Spanish | 1444 | 1400 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Grok 4.7: 74.1 (#105)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1404 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Grok 4.7: 43.1 (#104)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1446 | 1413 |
Writing & Preference Grok 4.7 leads
Gemma 4 31B IT: 60.5 (#96), Grok 4.7: 70.0 (#24)
| Benchmark | Gemma 4 31B IT | Grok 4.7 |
|---|---|---|
| LMArena Text | 1443 | 1399 |
| LMArena Creative Writing | 1415 | 1391 |
| EQ-Bench Creative Writing | 1368 | 2007 |
| LMArena Multi-Turn | 1452 | 1393 |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Grok 4.7?
Grok 4.7 is the stronger model overall, scoring 53.1 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 20× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Grok 4.7?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Grok 4.7 lists at $2 and $6.
Is Gemma 4 31B IT or Grok 4.7 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
Grok 4.7 does, with 500K tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Grok 4.7 share?
27 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Grok 4.7 has 39.