Model comparison
Gemma 4 31B IT vs Grok-3 mini
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Gemma 4 31B IT scores higher in 6 categories and Grok-3 mini in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 4 31B IT leads 27.2 to 13.6.
- The biggest single-benchmark swing is WeirdML: 52.3% for Gemma 4 31B IT and 42.6% for Grok-3 mini.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Grok-3 mini | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 43.5 | 41.2 |
| Released | 2026-04-02 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), Grok-3 mini: 40.8 (#131)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| WeirdML | 52.3% | 42.6% |
| LMArena Coding | 1459 | 1379 |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| ALE-Bench | 925.5 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Grok-3 mini: 13.6 (#334)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 61.3% |
| LMArena Hard Prompts | 1448 | 1375 |
| Epoch Capabilities Index | 142.74 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| NYT Connections (extended) | 70.6% | — |
| ARC-AGI-1 | — | 16.5% |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Grok-3 mini: 42.1 (#85)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 77.8% |
| LMArena Math | 1465 | 1386 |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Gemma 4 31B IT: 37.9 (#151), Grok-3 mini: 46.4 (#81)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 75.8% | 76.3% |
| LMArena Expert | 1465 | 1395 |
| SimpleQA Verified | 10.4% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 7.4% | — |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Grok-3 mini: —
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Grok-3 mini: 48.1 (#145)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1431 | 1352 |
| LMArena Chinese | 1476 | 1387 |
| LMArena French | 1435 | 1357 |
| LMArena Russian | 1460 | 1353 |
| LMArena Spanish | 1444 | 1381 |
| LMArena German | — | 1349 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1335 |
Instruction Following Grok-3 mini leads
Gemma 4 31B IT: 75.5 (#61), Grok-3 mini: 78.5 (#9)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1433 | 1357 |
| IFEval | — | 95.1% |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Grok-3 mini: 41.0 (#147)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1446 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Grok-3 mini: 52.5 (#169)
| Benchmark | Gemma 4 31B IT | Grok-3 mini |
|---|---|---|
| LMArena Text | 1443 | 1370 |
| LMArena Creative Writing | 1415 | 1342 |
| LMArena Multi-Turn | 1452 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1368 | — |
| WildBench | — | 65.1% |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Grok-3 mini?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.2 on the Noometry Index.
Is Gemma 4 31B IT or Grok-3 mini better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 40.8 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and Grok-3 mini share?
19 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Grok-3 mini has 35.