Model comparison
Gemma 4 26B A4B IT vs gpt-oss-20b
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 32.5 on the Noometry Index. gpt-oss-20b costs 4.0× less per token, which makes it the better buy when Gemma 4 26B A4B IT's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 8 categories and gpt-oss-20b in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 26B A4B IT leads 58.6 to 35.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 82.2% for Gemma 4 26B A4B IT and 65.3% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.09 / $0.30 for Gemma 4 26B A4B IT.
- Gemma 4 26B A4B IT accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 4 26B A4B IT | gpt-oss-20b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 43.5 | 32.5 |
| Released | 2026-04-02 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 33K | 16K |
| Input $ / M tokens | $0.09 | $0.018 |
| Output $ / M tokens | $0.30 | $0.09 |
| Results tracked | 28 | 34 |
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), gpt-oss-20b: 37.6 (#192)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| SciCode | 40% | 34.4% |
| WeirdML | 35.2% | 40.9% |
| LMArena Coding | 1447 | 1306 |
| ALE-Bench | 927.17 | 566.05 |
| LMArena WebDev | 1359 | — |
Agentic & Tool Use Not comparable
Gemma 4 26B A4B IT: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 21.8 (#213), gpt-oss-20b: 19.3 (#261)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| CritPt | 0% | 1.4% |
| Chess Puzzles | 6% | 4% |
| LMArena Hard Prompts | 1439 | 1274 |
| DTBench | 74.9% | 68% |
| LMCA | 29.7% | 14.5% |
| Epoch Capabilities Index | 141.85 | 137.82 |
| Kagi LLM Benchmark | — | 53.2% |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), gpt-oss-20b: 39.4 (#103)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 65.3% |
| LMArena Math | 1470 | 1317 |
| Omni-MATH | — | 56.5% |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#85), gpt-oss-20b: 34.6 (#195)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 73.2% | 60.8% |
| LMArena Expert | 1447 | 1258 |
| MMLU-Pro | — | 74% |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | — | 59.4% |
Multimodal Not comparable
Gemma 4 26B A4B IT: 40.6 (#46), gpt-oss-20b: —
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.1 (#71), gpt-oss-20b: 42.2 (#197)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1421 | 1268 |
| LMArena Chinese | 1495 | 1314 |
| LMArena Russian | 1434 | 1278 |
| LMArena Spanish | 1417 | 1267 |
| LMArena French | 1460 | — |
| LMArena German | — | 1255 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 74.8 (#82), gpt-oss-20b: 61.8 (#240)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1420 | 1236 |
| IFEval | — | 73.2% |
Long Context Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 43.6 (#91), gpt-oss-20b: 37.9 (#209)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1428 | 1250 |
Writing & Preference Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 58.6 (#115), gpt-oss-20b: 35.5 (#265)
| Benchmark | Gemma 4 26B A4B IT | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1434 | 1287 |
| LMArena Creative Writing | 1402 | 1201 |
| EQ-Bench Creative Writing | 1305 | 666 |
| LMArena Multi-Turn | 1441 | 1268 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Gemma 4 26B A4B IT better than gpt-oss-20b?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 32.5 on the Noometry Index. gpt-oss-20b costs 4.0× less per token, which makes it the better buy when Gemma 4 26B A4B IT's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 26B A4B IT or gpt-oss-20b?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Gemma 4 26B A4B IT lists at $0.09 and $0.30.
Is Gemma 4 26B A4B IT or gpt-oss-20b better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 26B A4B IT does, with 262K tokens against 131K.
How many benchmarks do Gemma 4 26B A4B IT and gpt-oss-20b share?
24 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and gpt-oss-20b has 34.