Compare / Gemma 4 E4B vs gpt-oss-20b
Gemma 4 E4B vs gpt-oss-20b
Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 2 sources that measured both models.
Of the 15 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Google vs OpenAI, every model from both labs.
Gemma 4 E4B or gpt-oss-20b? The short answer
They score and cost about the same; gpt-oss-20b writes faster. Pick on the results below that match your work.
- gpt-oss-20b scores higher on the Artificial Analysis Intelligence Index: 10.0 against 8.9.
- gpt-oss-20b writes faster: 277 tokens a second against 32.
- Gemma 4 E4B is newer: released 3 Apr 2026, against 5 Aug 2025 for gpt-oss-20b.
- On third-party benchmarks, on the results both models have: gpt-oss-20b does better for agents and tool use, reasoning and knowledge and writing.
Head to head
Every fact side by side
| Gemma 4 E4B | gpt-oss-20b | |
|---|---|---|
| Price per million tokens | Not on sale | $0.030 in · $0.14 out |
| Blended (3 in : 1 out) | – | $0.058 |
| Cheapest host, blended | – | $0.022 (PrimeIntellect, FP4) |
| Intelligence Index | 8.9 | 10.0 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 32 | 277 |
| Context window | – | 131,072 tokens |
| Released | 3 Apr 2026 (newer) | 5 Aug 2025 |
| Weights | Closed | Open |
| Developer based in | the US | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Gemma 4 E4B | gpt-oss-20b |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 191 · 176 of 249 measured | 8.9 | 10.0low reasoning |
| GPQA Diamond% of questions, higher is better 190 · 159 of 232 measured | 57.6% | 68.8%high reasoning |
| Humanity's Last Exam% of questions, higher is better 202 · 153 of 250 measured | 4.8%no reasoning | 11.0%high reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 197 · 182 of 230 measured | 21.6channel-thought-prefill reasoning | 24.6low reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 43 · 221 of 230 measured | 10.0%channel-thought-prefill reasoning | 98.0%low reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 199 · 187 of 230 measured | 0.30channel-thought-prefill reasoning | 0.31medium reasoning |
Show all 15 results (9 more)
| Measure | Gemma 4 E4B | gpt-oss-20b |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 9 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 124 · 97 of 131 measured | 1.9% | 13.9%high reasoning |
| Terminal-Bench 4.0% of tasks, higher is better 72 · 72 of 120 measured | 0.0% | 0.0%high reasoning |
| IFBench% of instructions, higher is better 117 · 69 of 195 measured | 44.2% | 65.1%high reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 191 · 184 of 241 measured | 32.0% | 34.7%high reasoning |
| Output speedtokens per second, higher is better 77 · 6 of 78 measured | 31.7no reasoning | 277low reasoning |
| SciCode% of problems, higher is better 115 · 90 of 121 measured | 24.4% | 38.9%high reasoning |
| Terminal-Bench Hard% of tasks, higher is better 131 · 127 of 190 measured | 8.3% | 10.6%high reasoning |
| Time to first answer tokenseconds, lower is better 5 · 44 of 78 measured | 0.43no reasoning | 7.62low reasoning |
| τ²-bench telecom% of tasks, higher is better 149 · 96 of 193 measured | 26.0%no reasoning | 60.2%high reasoning |
Compare them with other models
Quick answers
Is Gemma 4 E4B better than gpt-oss-20b?
They score and cost about the same; gpt-oss-20b writes faster. Pick on the results below that match your work.
Which is faster, Gemma 4 E4B or gpt-oss-20b?
gpt-oss-20b writes about 277 tokens a second on its usual API, against 32 for Gemma 4 E4B (Artificial Analysis).
Which is better for agents and tool use, Gemma 4 E4B or gpt-oss-20b?
gpt-oss-20b ranks 130 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 149 for Gemma 4 E4B.
Which is better for reasoning and knowledge, Gemma 4 E4B or gpt-oss-20b?
gpt-oss-20b ranks 132 of 188 models on sale for hard questions across science, maths and general knowledge, against 153 for Gemma 4 E4B.
Which is better for writing, Gemma 4 E4B or gpt-oss-20b?
gpt-oss-20b ranks 155 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 167 for Gemma 4 E4B.
Run Gemma 4 E4B and gpt-oss-20b on your own prompt.
Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.