Model comparison
Gemma 4 31B IT vs Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 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 Multi-Agent's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Gemma 4 31B IT scores higher in 4 categories and Grok 4.20 Multi-Agent in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 27.2.
- The biggest single-benchmark swing is NYT Connections (extended): 70.6% for Gemma 4 31B IT and 89.6% for Grok 4.20 Multi-Agent.
- 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 Multi-Agent.
- Grok 4.20 Multi-Agent 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 Multi-Agent | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 43.5 | 46.2 |
| Released | 2026-04-02 | 2026-03-09 |
| 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 | 20 |
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 Multi-Agent: 43.0 (#92)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1459 | 1457 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Grok 4.20 Multi-Agent: —
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | — | 1204 |
Reasoning Grok 4.20 Multi-Agent leads
Gemma 4 31B IT: 27.2 (#122), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| NYT Connections (extended) | 70.6% | 89.6% |
| LMArena Hard Prompts | 1448 | 1448 |
| Kagi LLM Benchmark | 63.5% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1465 | 1442 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Grok 4.20 Multi-Agent leads
Gemma 4 31B IT: 37.9 (#151), Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1465 | 1445 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.6 (#34), Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 1277 | 1259 |
| LMArena Document | 1425 | — |
Multilingual Too close to call
Gemma 4 31B IT: 53.8 (#57), Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1431 | 1440 |
| LMArena Chinese | 1476 | 1475 |
| LMArena French | 1435 | 1466 |
| LMArena Russian | 1460 | 1457 |
| LMArena Spanish | 1444 | 1447 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1416 |
Instruction Following Too close to call
Gemma 4 31B IT: 75.5 (#61), Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1433 | 1420 |
Long Context Too close to call
Gemma 4 31B IT: 44.2 (#71), Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1446 | 1431 |
Writing & Preference Grok 4.20 Multi-Agent leads
Gemma 4 31B IT: 60.5 (#96), Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | Gemma 4 31B IT | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1443 | 1450 |
| LMArena Creative Writing | 1415 | 1436 |
| LMArena Multi-Turn | 1452 | 1452 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 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 Multi-Agent's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Grok 4.20 Multi-Agent?
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 Multi-Agent lists at $1.25 and $2.50.
Is Gemma 4 31B IT or Grok 4.20 Multi-Agent better for coding?
They score almost the same on coding (42.3 vs 43.0); test both on your own repository before choosing.
Which has the bigger context window?
Grok 4.20 Multi-Agent does, with 1M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Grok 4.20 Multi-Agent share?
16 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Grok 4.20 Multi-Agent has 20.