Gemma 4 31B benchmark ranking on every AI leaderboard
open weights · top 10 on 0 of 7 · released Apr 2, 2026
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 30 |  Document ArenaVision · as “gemma-4-31b” | Vision | 1,425 | 38 | |
| 32 | Vision ArenaVision · as “gemma-4-31b” | Vision | 1,261 | 100 | |
| 55 | Text ArenaChat · as “gemma-4-31b” | Chat | 1,451 | 100 | |
| 63 |  AA IntelligenceReasoning · as “Gemma 4 31B (Reasoning)” | Reasoning | 19.0 | 100 | |
| 75 | WebDev ArenaCoding · as “gemma-4-31b” | Coding | 1,364 | 100 | |
| 84 |  GPQA DiamondReasoning · as “gemma-4-31b-it_minimal” | Reasoning | 75.8% | 100 | |
| 89 | Epoch ECIReasoning · as “Gemma 4 31B IT” | Reasoning | 142.7 | 100 |
Category ranks and more models
Sources: each leaderboard's own published results page, captured every day at 04:30 UTC. Scores exactly as each board published them; we run no evaluations. Logos via logo.dev; trademarks belong to their owners.