Model comparison
Gemma 4 31B IT vs Ring-2.6-1T
Gemma 4 31B IT has enough public results to be ranked (#90); Ring-2.6-1T does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Google
Ant Group (inclusionAI)Summary
- They share 3 benchmarks with published results for both. Gemma 4 31B IT scores higher in 2 categories and Ring-2.6-1T in 0 categories; 2 gaps are clear of the uncertainty.
Side by side
| Gemma 4 31B IT | Ring-2.6-1T | |
|---|---|---|
| Provider | Ant Group (inclusionAI) | |
| Noometry Index | 43.5 | 36.9 |
| Released | 2026-04-02 | 2026-05-14 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 3 |
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), Ring-2.6-1T: 40.7
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| SciCode | 43.4% | 42.4% |
| ALE-Bench | 925.5 | 432.57 |
| LMArena WebDev | 1366 | — |
| WeirdML | 52.3% | — |
| LMArena Coding | 1459 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Ring-2.6-1T: 26.1
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| CritPt | 1.4% | 3.7% |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| LMArena Hard Prompts | 1448 | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Not comparable
Gemma 4 31B IT: 43.2 (#81), Ring-2.6-1T: —
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| LMArena Math | 1465 | — |
Knowledge Not comparable
Gemma 4 31B IT: 37.9 (#151), Ring-2.6-1T: —
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1465 | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Ring-2.6-1T: —
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Not comparable
Gemma 4 31B IT: 53.8 (#57), Ring-2.6-1T: —
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1476 | — |
| LMArena French | 1435 | — |
| LMArena Russian | 1460 | — |
| LMArena Spanish | 1444 | — |
Instruction Following Not comparable
Gemma 4 31B IT: 75.5 (#61), Ring-2.6-1T: —
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
Gemma 4 31B IT: 44.2 (#71), Ring-2.6-1T: —
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| LMArena Longer Query | 1446 | — |
Writing & Preference Not comparable
Gemma 4 31B IT: 60.5 (#96), Ring-2.6-1T: —
| Benchmark | Gemma 4 31B IT | Ring-2.6-1T |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1415 | — |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
| LMArena Multi-Turn | 1452 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Ring-2.6-1T?
Gemma 4 31B IT has enough public results to be ranked (#90); Ring-2.6-1T does not yet, so treat this comparison as directional.
Is Gemma 4 31B IT or Ring-2.6-1T better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 40.7 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and Ring-2.6-1T share?
3 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Ring-2.6-1T has 3.