Compare / Gemma 4 12B vs gpt-oss-120b
Gemma 4 12B vs gpt-oss-120b
Which is cheaper, which is more capable, and which does better at each kind of work, from 14 results on 2 sources that measured both models.
Of the 14 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 12B or gpt-oss-120b? The short answer
Pick Gemma 4 12B: it scores higher (Intelligence Index 14.2 against 11.6) at about the same price. Pick gpt-oss-120b only if speed matters more: it writes faster.
- Gemma 4 12B scores higher on the Artificial Analysis Intelligence Index: 14.2 against 11.6.
- gpt-oss-120b writes faster: 259 tokens a second against 148.
- Gemma 4 12B is newer: released 3 Jun 2026, against 5 Aug 2025 for gpt-oss-120b.
- On third-party benchmarks, on the results both models have: Gemma 4 12B does better for agents and tool use; gpt-oss-120b for reasoning and knowledge and writing.
Head to head
Every fact side by side
| Gemma 4 12B | gpt-oss-120b | |
|---|---|---|
| Price per million tokens | Not on sale | $0.10 in · $0.50 out |
| Blended (3 in : 1 out) | – | $0.20 |
| Cheapest host, blended | – | $0.060 (Near AI, FP4) |
| Intelligence Index | 14.2 | 11.6 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 148 | 259 |
| Context window | – | 131,072 tokens |
| Released | 3 Jun 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 12B | gpt-oss-120b |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 139 · 162 of 249 measured | 14.2 | 11.6high reasoning |
| GPQA Diamond% of questions, higher is better 137 · 119 of 232 measured | 75.3% | 78.2%high reasoning |
| Humanity's Last Exam% of questions, higher is better 133 · 118 of 250 measured | 15.7% | 19.6%high reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 121 · 116 of 230 measured | 36.3channel-thought-prefill reasoning | 38.5medium reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 25 · 224 of 230 measured | 8.0% | 107.0%medium reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 117 · 217 of 230 measured | 0.35 | 0.29medium reasoning |
Show all 14 results (8 more)
| Measure | Gemma 4 12B | gpt-oss-120b |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 8 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 86 · 88 of 131 measured | 27.3% | 26.2%high reasoning |
| Artificial Analysis Coding Indexindex score, higher is better 84 · 85 of 130 measured | 31.0 | 30.4high reasoning |
| IFBench% of instructions, higher is better 32 · 58 of 195 measured | 73.5% | 69.0%high reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 139 · 160 of 241 measured | 63.7% | 52.0%high reasoning |
| Output speedtokens per second, higher is better 26 · 8 of 78 measured | 148 | 259high reasoning |
| Terminal-Bench Hard% of tasks, higher is better 97 · 84 of 190 measured | 18.2% | 23.5%high reasoning |
| Time to first answer tokenseconds, lower is better 29 · 45 of 78 measured | 1.15no reasoning | 8.22high reasoning |
| τ²-bench telecom% of tasks, higher is better 121 · 86 of 193 measured | 36.3% | 65.8%high reasoning |
Compare them with other models
Quick answers
Is Gemma 4 12B better than gpt-oss-120b?
Pick Gemma 4 12B: it scores higher (Intelligence Index 14.2 against 11.6) at about the same price. Pick gpt-oss-120b only if speed matters more: it writes faster.
Which is faster, Gemma 4 12B or gpt-oss-120b?
gpt-oss-120b writes about 259 tokens a second on its usual API, against 148 for Gemma 4 12B (Artificial Analysis).
Which is better for agents and tool use, Gemma 4 12B or gpt-oss-120b?
Gemma 4 12B ranks 115 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 125 for gpt-oss-120b.
Which is better for reasoning and knowledge, Gemma 4 12B or gpt-oss-120b?
gpt-oss-120b ranks 118 of 188 models on sale for hard questions across science, maths and general knowledge, against 121 for Gemma 4 12B.
Which is better for writing, Gemma 4 12B or gpt-oss-120b?
Gemma 4 12B ranks 118 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 124 for gpt-oss-120b.
Run Gemma 4 12B and gpt-oss-120b 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.