Compare / Llama 3.1 8B Instruct vs gpt-oss-20b

Llama 3.1 8B Instruct vs gpt-oss-20b

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 3 sources that measured both models.

MetaLlama 3.1 8B Instruct Released 23 Jul 2024 · $0.050 in · $0.080 out
OpenAIgpt-oss-20b Released 5 Aug 2025 · $0.030 in · $0.14 out
Llama 3.1 8B Instruct wins 3gpt-oss-20b wins 15

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 21 November 2026 (catalogue release 2026-11-21-af3a2faf6a5c). See also Meta vs OpenAI, every model from both labs.

Llama 3.1 8B Instruct or gpt-oss-20b? The short answer

Pick gpt-oss-20b: it scores higher (Intelligence Index 10.0 against 6.9) at about the same price.

  • They cost about the same: $0.058 and $0.058 per million tokens (three input to one output).
  • gpt-oss-20b scores higher on the Artificial Analysis Intelligence Index: 10.0 against 6.9.
  • gpt-oss-20b is newer: released 5 Aug 2025, against 23 Jul 2024 for Llama 3.1 8B Instruct.
  • On third-party benchmarks, on the results both models have: gpt-oss-20b does better for agents and tool use and reasoning and knowledge.

Head to head

6.9
Intelligence Index
10.0
$0.058
Price per million tokens, blendedlower is better
$0.058
131,072
Context window, tokens
131,072

Every fact side by side

Llama 3.1 8B Instructgpt-oss-20b
Price per million tokens$0.050 in · $0.080 out$0.030 in · $0.14 out
Blended (3 in : 1 out)$0.058$0.058
Cheapest host, blended$0.025 (DeepInfra, FP8)$0.022 (PrimeIntellect, FP4)
Intelligence Index6.910.0
Spring Prompt overall––
Output speed, tokens a second–277
Context window131,072 tokens131,072 tokens
Released23 Jul 20245 Aug 2025 (newer)
WeightsOpenOpen
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 153 of 159 130 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 166 of 187 132 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 164 of 169 155 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.

MeasureLlama 3.1 8B Instructgpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 314 · 237 of 387 measured 1,211 1,318
Business, management and finance · TextArena rating, higher is better 308 · 213 of 380 measured 1,210 1,323
Creative writing · TextArena rating, higher is better 313 · 275 of 385 measured 1,177 1,240
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 222 · 176 of 249 measured 6.9 10.0low reasoning
GPQA Diamond% of questions, higher is better 228 · 159 of 232 measured 25.9% 68.8%high reasoning
Humanity's Last Exam% of questions, higher is better 194 · 153 of 250 measured 5.3% 11.0%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 181 · 182 of 230 measured 24.8 24.6low reasoning
Requested-length error · UGI% off the requested word count, lower is better 111 · 221 of 230 measured 20.0% 98.0%low reasoning
Style adherence · UGIscore from 0 to 1, higher is better 122 · 187 of 230 measured 0.34 0.31medium reasoning
Show all 18 results (9 more)
MeasureLlama 3.1 8B Instructgpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 304 · 220 of 338 measured 1,198 1,314
Instruction following · TextArena rating, higher is better 315 · 257 of 387 measured 1,191 1,281
Writing, literature and language · TextArena rating, higher is better 315 · 261 of 386 measured 1,182 1,275
Artificial Analysis reported by Artificial Analysis · 6 results
Terminal-Bench 2.1% of tasks, higher is better 125 · 97 of 131 measured 1.5% 13.9%high reasoning
Artificial Analysis Coding Indexindex score, higher is better 126 · 100 of 130 measured 5.4 20.7high reasoning
IFBench% of instructions, higher is better 186 · 69 of 195 measured 28.6% 65.1%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 215 · 184 of 241 measured 18.0% 34.7%high reasoning
Terminal-Bench Hard% of tasks, higher is better 180 · 127 of 190 measured 0.8% 10.6%high reasoning
τ²-bench telecom% of tasks, higher is better 174 · 96 of 193 measured 16.4% 60.2%high reasoning

Quick answers

Is Llama 3.1 8B Instruct better than gpt-oss-20b?

Pick gpt-oss-20b: it scores higher (Intelligence Index 10.0 against 6.9) at about the same price.

Which is cheaper, Llama 3.1 8B Instruct or gpt-oss-20b?

They cost about the same: $0.058 and $0.058 per million tokens (three input to one output).

Which is better for agents and tool use, Llama 3.1 8B Instruct or gpt-oss-20b?

gpt-oss-20b ranks 130 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 153 for Llama 3.1 8B Instruct.

Which is better for reasoning and knowledge, Llama 3.1 8B Instruct or gpt-oss-20b?

gpt-oss-20b ranks 132 of 187 models on sale for hard questions across science, maths and general knowledge, against 166 for Llama 3.1 8B Instruct.

Which is better for writing, Llama 3.1 8B Instruct or gpt-oss-20b?

gpt-oss-20b ranks 155 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 164 for Llama 3.1 8B Instruct.

Run Llama 3.1 8B Instruct 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.