Model comparison
Gemma 4 26B A4B IT vs Olmo 3 32b Think
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 38.7 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 26B A4B IT scores higher in 7 categories and Olmo 3 32b Think in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 4 26B A4B IT leads 53.1 to 41.2.
Side by side
| Gemma 4 26B A4B IT | Olmo 3 32b Think | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 43.5 | 38.7 |
| Released | 2026-04-02 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.0675 | — |
| Output $ / M tokens | $0.23 | — |
| Results tracked | 28 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 4 26B A4B IT: 39.0 (#164), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1447 | 1319 |
| LMArena WebDev | 1359 | — |
| SciCode | 40% | — |
| WeirdML | 35.2% | — |
| ALE-Bench | 927.17 | — |
Reasoning Olmo 3 32b Think leads
Gemma 4 26B A4B IT: 21.8 (#213), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1439 | 1302 |
| CritPt | 0% | — |
| Chess Puzzles | 6% | — |
| DTBench | 74.9% | — |
| LMCA | 29.7% | — |
| Epoch Capabilities Index | 141.85 | — |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1470 | 1316 |
| OTIS Mock AIME 2024-2025 | 82.2% | — |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#85), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1447 | 1273 |
| GPQA Diamond | 73.2% | — |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Not comparable
Gemma 4 26B A4B IT: 40.6 (#46), Olmo 3 32b Think: —
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.1 (#71), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1421 | 1255 |
| LMArena Chinese | 1495 | 1300 |
| LMArena French | 1460 | 1291 |
| LMArena Russian | 1434 | 1254 |
| LMArena German | — | 1290 |
| LMArena Spanish | 1417 | — |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 74.8 (#82), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1420 | 1275 |
Long Context Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 43.6 (#91), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1428 | 1296 |
Writing & Preference Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 58.6 (#115), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | Gemma 4 26B A4B IT | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1434 | 1300 |
| LMArena Creative Writing | 1402 | 1256 |
| LMArena Multi-Turn | 1441 | 1290 |
| EQ-Bench Creative Writing | 1305 | — |
Frequently asked questions
Is Gemma 4 26B A4B IT better than Olmo 3 32b Think?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 38.7 on the Noometry Index.
Is Gemma 4 26B A4B IT or Olmo 3 32b Think better for coding?
They score almost the same on coding (39.0 vs 38.6); test both on your own repository before choosing.
How many benchmarks do Gemma 4 26B A4B IT and Olmo 3 32b Think share?
13 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Olmo 3 32b Think has 14.