Model comparison
Gemma 4 31B IT vs Grok-2 (Dec 2024)
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 33.7 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 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 11.5% for Grok-2 (Dec 2024).
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 43.5 | 33.7 |
| Released | 2026-04-02 | 2024-08-13 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 34 |
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-2 (Dec 2024): 33.3 (#258)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 52.3% | 22.2% |
| LMArena Coding | 1459 | 1287 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 925.5 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1272 |
| DTBench | 82.7% | 65.2% |
| Epoch Capabilities Index | 142.74 | 130.48 |
| SimpleBench | — | 22.7% |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| LiveBench Reasoning | — | 54.8% |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| LiveBench | — | 54.3% |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 11.5% |
| LMArena Math | 1465 | 1283 |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#151), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 75.8% | 53.8% |
| LMArena Expert | 1465 | 1254 |
| SimpleQA Verified | 10.4% | — |
| Confabulations | — | 20.1% |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Grok-2 (Dec 2024): —
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1431 | 1282 |
| LMArena Chinese | 1476 | 1289 |
| LMArena French | 1435 | 1318 |
| LMArena Russian | 1460 | 1286 |
| LMArena Spanish | 1444 | 1281 |
| LMArena German | — | 1287 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1237 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1433 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1446 | 1276 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | Gemma 4 31B IT | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1443 | 1305 |
| LMArena Creative Writing | 1415 | 1284 |
| LMArena Multi-Turn | 1452 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is Gemma 4 31B IT better than Grok-2 (Dec 2024)?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 33.7 on the Noometry Index.
Is Gemma 4 31B IT or Grok-2 (Dec 2024) better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 33.3 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and Grok-2 (Dec 2024) share?
19 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Grok-2 (Dec 2024) has 34.