Compare / Llama 3.3 70B Instruct vs gpt-oss-20b
Llama 3.3 70B Instruct vs gpt-oss-20b
Which is cheaper, which is more capable, and which does better at each kind of work, from 20 results on 3 sources that measured both models.
Of the 20 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331). See also Meta vs OpenAI, every model from both labs.
Llama 3.3 70B Instruct or gpt-oss-20b? The short answer
Pick gpt-oss-20b: it scores higher (Intelligence Index 10.0 against 7.7) and costs less.
- gpt-oss-20b is cheaper: $0.058 against $0.71 per million tokens, 12 times less.
- gpt-oss-20b scores higher on the Artificial Analysis Intelligence Index: 10.0 against 7.7.
- gpt-oss-20b writes faster: 277 tokens a second against 98.
- gpt-oss-20b is newer: released 5 Aug 2025, against 6 Dec 2024 for Llama 3.3 70B Instruct.
- On third-party benchmarks, on the results both models have: Llama 3.3 70B Instruct does better for writing; gpt-oss-20b for agents and tool use and reasoning and knowledge.
Head to head
Every fact side by side
| Llama 3.3 70B Instruct | gpt-oss-20b | |
|---|---|---|
| Price per million tokens | $0.71 in · $0.71 out | $0.030 in · $0.14 out |
| Blended (3 in : 1 out) | $0.71 | $0.058 |
| Cheapest host, blended | $0.16 (DeepInfra, FP8) | $0.022 (PrimeIntellect, FP4) |
| Intelligence Index | 7.7 | 10.0 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 98 | 277 |
| Context window | 131,072 tokens | 131,072 tokens |
| Released | 6 Dec 2024 | 5 Aug 2025 (newer) |
| Weights | Open | 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.
From our research
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 | Llama 3.3 70B Instruct | gpt-oss-20b |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 235 · 237 of 387 measured | 1,318 | 1,318 |
| Business, management and finance · TextArena rating, higher is better 240 · 213 of 380 measured | 1,304 | 1,323 |
| Creative writing · TextArena rating, higher is better 228 · 275 of 385 measured | 1,285 | 1,240 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 205 · 176 of 249 measured | 7.7 | 10.0low reasoning |
| GPQA Diamond% of questions, higher is better 204 · 159 of 232 measured | 49.8% | 68.8%high reasoning |
| Humanity's Last Exam% of questions, higher is better 237 · 153 of 250 measured | 3.6% | 11.0%high reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 171 · 182 of 230 measured | 26.2 | 24.6low reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 43 · 221 of 230 measured | 10.0% | 98.0%low reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 51 · 187 of 230 measured | 0.37 | 0.31medium reasoning |
Show all 20 results (11 more)
| Measure | Llama 3.3 70B Instruct | gpt-oss-20b |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 237 · 220 of 338 measured | 1,298 | 1,314 |
| Instruction following · TextArena rating, higher is better 244 · 257 of 387 measured | 1,293 | 1,281 |
| Writing, literature and language · TextArena rating, higher is better 242 · 261 of 386 measured | 1,292 | 1,275 |
| Artificial Analysis reported by Artificial Analysis · 8 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 113 · 97 of 131 measured | 4.9% | 13.9%high reasoning |
| Artificial Analysis Coding Indexindex score, higher is better 117 · 100 of 130 measured | 11.9 | 20.7high reasoning |
| IFBench% of instructions, higher is better 112 · 69 of 195 measured | 47.1% | 65.1%high reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 219 · 184 of 241 measured | 15.7% | 34.7%high reasoning |
| Output speedtokens per second, higher is better 44 · 6 of 78 measured | 97.7 | 277low reasoning |
| Terminal-Bench Hard% of tasks, higher is better 169 · 127 of 190 measured | 3.0% | 10.6%high reasoning |
| Time to first answer tokenseconds, lower is better 14 · 44 of 78 measured | 0.64 | 7.62low reasoning |
| τ²-bench telecom% of tasks, higher is better 146 · 96 of 193 measured | 26.6% | 60.2%high reasoning |
Compare them with other models
Quick answers
Is Llama 3.3 70B Instruct better than gpt-oss-20b?
Pick gpt-oss-20b: it scores higher (Intelligence Index 10.0 against 7.7) and costs less.
Which is cheaper, Llama 3.3 70B Instruct or gpt-oss-20b?
gpt-oss-20b is cheaper: $0.058 against $0.71 per million tokens, 12 times less.
Which is faster, Llama 3.3 70B Instruct or gpt-oss-20b?
gpt-oss-20b writes about 277 tokens a second on its usual API, against 98 for Llama 3.3 70B Instruct (Artificial Analysis).
Which is better for agents and tool use, Llama 3.3 70B Instruct or gpt-oss-20b?
Llama 3.3 70B Instruct ranks 127 of 159 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, Llama 3.3 70B 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 164 for Llama 3.3 70B Instruct.
Which is better for writing, Llama 3.3 70B Instruct or gpt-oss-20b?
Llama 3.3 70B Instruct ranks 151 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 155 for gpt-oss-20b.
Run Llama 3.3 70B 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.