Model comparison
Gemma 4 26B A4B IT vs o1-mini
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 34.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 8 categories and o1-mini in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 4 26B A4B IT leads 21.8 to 8.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 82.2% for Gemma 4 26B A4B IT and 46.9% for o1-mini.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 26B A4B IT | o1-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 43.5 | 34.0 |
| Released | 2026-04-02 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.0675 | — |
| Output $ / M tokens | $0.23 | — |
| Results tracked | 28 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 39.0 (#164), o1-mini: 35.5 (#224)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| WeirdML | 35.2% | 36.3% |
| LMArena Coding | 1447 | 1362 |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1359 | — |
| SciCode | 40% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 927.17 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
Gemma 4 26B A4B IT: —, o1-mini: 24.6 (#118)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 21.8 (#213), o1-mini: 8.8 (#346)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1439 | 1333 |
| Epoch Capabilities Index | 141.85 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| CritPt | 0% | — |
| Chess Puzzles | 6% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 74.9% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 29.7% | — |
| LiveBench | — | 57.8% |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), o1-mini: 35.4 (#186)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 46.9% |
| LMArena Math | 1470 | 1358 |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#85), o1-mini: 34.9 (#192)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| GPQA Diamond | 73.2% | 62.4% |
| LMArena Expert | 1447 | 1316 |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Not comparable
Gemma 4 26B A4B IT: 40.6 (#46), o1-mini: —
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.1 (#71), o1-mini: 43.6 (#182)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| LMArena Non-English | 1421 | 1289 |
| LMArena Chinese | 1495 | 1314 |
| LMArena French | 1460 | 1293 |
| LMArena Russian | 1434 | 1283 |
| LMArena Spanish | 1417 | 1303 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 74.8 (#82), o1-mini: 66.7 (#206)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1420 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 43.6 (#91), o1-mini: 40.1 (#161)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| LMArena Longer Query | 1428 | 1320 |
Writing & Preference Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 58.6 (#115), o1-mini: 48.4 (#202)
| Benchmark | Gemma 4 26B A4B IT | o1-mini |
|---|---|---|
| LMArena Text | 1434 | 1317 |
| LMArena Creative Writing | 1402 | 1244 |
| LMArena Multi-Turn | 1441 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1305 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Gemma 4 26B A4B IT better than o1-mini?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 34.0 on the Noometry Index.
Is Gemma 4 26B A4B IT or o1-mini better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 35.5 in the Noometry coding category.
How many benchmarks do Gemma 4 26B A4B IT and o1-mini share?
18 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and o1-mini has 39.