Model comparison
Gemma 4 31B IT vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 10× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Gemma 4 31B IT scores higher in 3 categories and Grok 4.20 (Non-Reasoning) in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 27.2.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 30.2% for Grok 4.20 (Non-Reasoning).
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 43.5 | 48.6 |
| Released | 2026-04-02 | 2026-02-17 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 33K | 30K |
| Input $ / M tokens | $0.09 | $1.25 |
| Output $ / M tokens | $0.34 | $2.50 |
| Results tracked | 35 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 4 31B IT: 42.3 (#108), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1366 | 1375 |
| WeirdML | 52.3% | 52.3% |
| LMArena Coding | 1459 | 1459 |
| ALE-Bench | 925.5 | 1,150 |
| SciCode | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
Gemma 4 31B IT: 27.2 (#122), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 75% |
| NYT Connections (extended) | 70.6% | 85.4% |
| Chess Puzzles | 5% | 24% |
| Thematic Generalization | 53% | 63.8% |
| LMArena Hard Prompts | 1448 | 1451 |
| DTBench | 82.7% | 90.1% |
| LMCA | 39.3% | 38.7% |
| Epoch Capabilities Index | 142.74 | 151.98 |
| ARC-AGI-2 | — | 65.1% |
| ARC-AGI-1 | — | 89.5% |
| CritPt | 1.4% | — |
| Surface Evolver Bench | 30.6% | — |
| ForecastBench | — | 61.4 |
Math Grok 4.20 (Non-Reasoning) leads
Gemma 4 31B IT: 43.2 (#81), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 92.2% |
| LMArena Math | 1465 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Gemma 4 31B IT: 37.9 (#151), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 75.8% | 89.3% |
| SimpleQA Verified | 10.4% | 30.2% |
| LMArena Expert | 1465 | 1439 |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.6 (#34), Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1277 | 1263 |
| LMArena Document | 1425 | 1416 |
| Blueprint-Bench 2 | — | 0% |
Multilingual Too close to call
Gemma 4 31B IT: 53.8 (#57), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1431 | 1441 |
| LMArena Chinese | 1476 | 1481 |
| LMArena French | 1435 | 1476 |
| LMArena Russian | 1460 | 1458 |
| LMArena Spanish | 1444 | 1443 |
| LMArena German | — | 1465 |
| LMArena Japanese | — | 1449 |
| LMArena Korean | — | 1417 |
Instruction Following Too close to call
Gemma 4 31B IT: 75.5 (#61), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1433 | 1420 |
Long Context Grok 4.20 (Non-Reasoning) leads
Gemma 4 31B IT: 44.2 (#71), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1446 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Gemma 4 31B IT: 60.5 (#96), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | Gemma 4 31B IT | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1443 | 1451 |
| LMArena Creative Writing | 1415 | 1438 |
| EQ-Bench Creative Writing | 1368 | 1574 |
| LMArena Multi-Turn | 1452 | 1456 |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 10× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Grok 4.20 (Non-Reasoning)?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Gemma 4 31B IT or Grok 4.20 (Non-Reasoning) better for coding?
They score almost the same on coding (42.3 vs 42.1); test both on your own repository before choosing.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Grok 4.20 (Non-Reasoning) share?
30 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.