Model comparison
Gemma 4 31B IT vs Olmo 3 32b Think
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 38.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Olmo 3 32b Think in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 4 31B IT leads 54.0 to 41.4.
Side by side
| Gemma 4 31B IT | Olmo 3 32b Think | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 43.2 | 38.1 |
| Released | 2026-04-02 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 14 |
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: 41.9 (#98), Olmo 3 32b Think: 38.0 (#169)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1459 | 1318 |
| LMArena WebDev | 1364 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 26.4 (#119), Olmo 3 32b Think: 24.9 (#138)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1302 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| 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: 41.3 (#72), Olmo 3 32b Think: 33.8 (#165)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1464 | 1315 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#141), Olmo 3 32b Think: 34.4 (#189)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1465 | 1272 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.0 (#32), Olmo 3 32b Think: —
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 54.0 (#52), Olmo 3 32b Think: 41.4 (#205)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1431 | 1255 |
| LMArena Chinese | 1478 | 1300 |
| LMArena French | 1436 | 1291 |
| LMArena Russian | 1462 | 1255 |
| LMArena German | — | 1290 |
| LMArena Spanish | 1443 | — |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.6 (#58), Olmo 3 32b Think: 67.4 (#193)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1433 | 1275 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#67), Olmo 3 32b Think: 39.4 (#177)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1446 | 1296 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.7 (#92), Olmo 3 32b Think: 49.2 (#188)
| Benchmark | Gemma 4 31B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1443 | 1300 |
| LMArena Creative Writing | 1416 | 1256 |
| LMArena Multi-Turn | 1452 | 1289 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Olmo 3 32b Think?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 38.1 on the Noometry Index.
Is Gemma 4 31B IT or Olmo 3 32b Think better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 38.0 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and Olmo 3 32b Think share?
13 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Olmo 3 32b Think has 14.