Compare / Mercury 2 vs gpt-oss-20b

Mercury 2 vs gpt-oss-20b

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 2 sources that measured both models.

InceptionMercury 2 Released 20 Feb 2026 · Not on sale
OpenAIgpt-oss-20b Released 5 Aug 2025 · $0.030 in · $0.14 out
Mercury 2 wins 134 too close to callgpt-oss-20b wins 1

Of the 18 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).

Mercury 2 or gpt-oss-20b? The short answer

They score and cost about the same: pick on the results below that match your work.

  • They score about the same on the Artificial Analysis Intelligence Index (10.8 and 10.0).
  • Mercury 2 is newer: released 20 Feb 2026, against 5 Aug 2025 for gpt-oss-20b.
  • On third-party benchmarks, on the results both models have: Mercury 2 does better for agents and tool use, reasoning and knowledge and writing.

Head to head

10.8
Intelligence Index
10.0

Every fact side by side

Mercury 2gpt-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 Index10.810.0
Spring Prompt overall––
Output speed, tokens a second–277
Context window–131,072 tokens
Released20 Feb 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 118 of 160 130 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 124 of 188 132 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 132 of 170 155 of 169
Sticking to the factsSummarising without inventing things, and factual answers 126 of 140 not measured

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.

MeasureMercury 2gpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 200 · 237 of 387 measured 1,343 1,318
Business, management and finance · TextArena rating, higher is better 202 · 213 of 380 measured 1,340 1,323
Creative writing · TextArena rating, higher is better 221 · 275 of 385 measured 1,292 1,240
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 171 · 176 of 249 measured 10.8 10.0low reasoning
GPQA Diamond% of questions, higher is better 129 · 159 of 232 measured 77.0% 68.8%high reasoning
Humanity's Last Exam% of questions, higher is better 126 · 153 of 250 measured 17.1% 11.0%high reasoning
Show all 18 results (12 more)
MeasureMercury 2gpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 196 · 220 of 338 measured 1,348 1,314
Instruction following · TextArena rating, higher is better 201 · 257 of 387 measured 1,326 1,281
Writing, literature and language · TextArena rating, higher is better 218 · 261 of 386 measured 1,308 1,275
Artificial Analysis reported by Artificial Analysis · 9 results
Terminal-Bench 2.1% of tasks, higher is better 86 · 97 of 131 measured 27.3% 13.9%high reasoning
Terminal-Bench 4.0% of tasks, higher is better 72 · 72 of 120 measured 0.0% 0.0%high reasoning
τ-bench banking% of tasks, higher is better 81 · 90 of 121 measured 9.5% 7.0%high reasoning
Artificial Analysis Coding Indexindex score, higher is better 83 · 100 of 130 measured 31.1 20.7high reasoning
IFBench% of instructions, higher is better 57 · 69 of 195 measured 69.8% 65.1%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 173 · 184 of 241 measured 43.7% 34.7%high reasoning
SciCode% of problems, higher is better 94 · 90 of 121 measured 37.7% 38.9%high reasoning
Terminal-Bench Hard% of tasks, higher is better 74 · 127 of 190 measured 26.5% 10.6%high reasoning
τ²-bench telecom% of tasks, higher is better 83 · 96 of 193 measured 70.8% 60.2%high reasoning

Quick answers

Is Mercury 2 better than gpt-oss-20b?

They score and cost about the same: pick on the results below that match your work.

Which is better for agents and tool use, Mercury 2 or gpt-oss-20b?

Mercury 2 ranks 118 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 130 for gpt-oss-20b.

Which is better for reasoning and knowledge, Mercury 2 or gpt-oss-20b?

Mercury 2 ranks 124 of 188 models on sale for hard questions across science, maths and general knowledge, against 132 for gpt-oss-20b.

Which is better for writing, Mercury 2 or gpt-oss-20b?

Mercury 2 ranks 132 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 155 for gpt-oss-20b.

Run Mercury 2 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.