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.

GoogleGemma 4 E4B Released 3 Apr 2026 · Not on sale
OpenAIgpt-oss-20b Released 5 Aug 2025 · $0.030 in · $0.14 out
Gemma 4 E4B wins 21 too close to callgpt-oss-20b wins 12

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

8.9
Intelligence Index
10.0
32
Output speed, tokens a second
277

Every fact side by side

Gemma 4 E4Bgpt-oss-20b
Price per million tokensNot on sale$0.030 in · $0.14 out
Blended (3 in : 1 out)–$0.058
Cheapest host, blended–$0.022 (PrimeIntellect, FP4)
Intelligence Index8.910.0
Spring Prompt overall––
Output speed, tokens a second32277
Context window–131,072 tokens
Released3 Apr 2026 (newer)5 Aug 2025
WeightsClosedOpen
Developer based inthe USthe 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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 149 of 160 130 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 153 of 188 132 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 167 of 170 155 of 169

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.

MeasureGemma 4 E4Bgpt-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)
MeasureGemma 4 E4Bgpt-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

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.