Compare / Llama 3.1 70B Instruct vs Llama 3.3 70B Instruct

Llama 3.1 70B Instruct vs Llama 3.3 70B Instruct

Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.

MetaLlama 3.1 70B Instruct Released 23 Jul 2024 · $0.72 in · $0.72 out
MetaLlama 3.3 70B Instruct Released 6 Dec 2024 · $0.71 in · $0.71 out
Llama 3.1 70B Instruct wins 32 too close to callLlama 3.3 70B Instruct wins 10

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 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

Llama 3.1 70B Instruct or Llama 3.3 70B Instruct? The short answer

Llama 3.3 70B Instruct is the newer version; they score about the same at about the same price.

  • They cost about the same: $0.72 and $0.71 per million tokens (three input to one output).
  • Llama 3.3 70B Instruct scores higher on the Artificial Analysis Intelligence Index: 7.7 against 6.6.
  • Llama 3.3 70B Instruct is newer: released 6 Dec 2024, against 23 Jul 2024 for Llama 3.1 70B Instruct.
  • On third-party benchmarks, on the results both models have: Llama 3.3 70B Instruct does better for reasoning and knowledge.

Head to head

6.6
Intelligence Index
7.7
$0.72
Price per million tokens, blendedlower is better
$0.71
131,072
Context window, tokens
131,072

Every fact side by side

Llama 3.1 70B InstructLlama 3.3 70B Instruct
Price per million tokens$0.72 in · $0.72 out$0.71 in · $0.71 out
Blended (3 in : 1 out)$0.72$0.71
Cheapest host, blended–$0.16 (DeepInfra, FP8)
Intelligence Index6.67.7
Spring Prompt overall––
Output speed, tokens a second–98
Context window131,072 tokens131,072 tokens
Released23 Jul 20246 Dec 2024 (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 not measured 127 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 172 of 187 164 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 140 of 169 151 of 169

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.

MeasureLlama 3.1 70B InstructLlama 3.3 70B Instruct
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 260 · 235 of 387 measured 1,293 1,318
Business, management and finance · TextArena rating, higher is better 258 · 240 of 380 measured 1,287 1,304
Creative writing · TextArena rating, higher is better 262 · 228 of 385 measured 1,257 1,285
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 231 · 205 of 249 measured 6.6 7.7
GPQA Diamond% of questions, higher is better 221 · 204 of 232 measured 40.9% 49.8%
Humanity's Last Exam% of questions, higher is better 210 · 237 of 250 measured 4.5% 3.6%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 135 · 171 of 230 measured 32.8 26.2
Requested-length error · UGI% off the requested word count, lower is better 69 · 43 of 230 measured 15.0% 10.0%
Style adherence · UGIscore from 0 to 1, higher is better 31 · 51 of 230 measured 0.38 0.37
Show all 15 results (6 more)
MeasureLlama 3.1 70B InstructLlama 3.3 70B Instruct
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 256 · 237 of 338 measured 1,275 1,298
Instruction following · TextArena rating, higher is better 264 · 244 of 387 measured 1,273 1,293
Writing, literature and language · TextArena rating, higher is better 272 · 242 of 386 measured 1,264 1,292
Artificial Analysis reported by Artificial Analysis · 3 results
IFBench% of instructions, higher is better 161 · 112 of 195 measured 34.4% 47.1%
Terminal-Bench Hard% of tasks, higher is better 169 · 169 of 190 measured 3.0% 3.0%
τ²-bench telecom% of tasks, higher is better 178 · 146 of 193 measured 15.2% 26.6%

Quick answers

Is Llama 3.1 70B Instruct better than Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct is the newer version; they score about the same at about the same price.

Which is cheaper, Llama 3.1 70B Instruct or Llama 3.3 70B Instruct?

They cost about the same: $0.72 and $0.71 per million tokens (three input to one output).

Which is better for reasoning and knowledge, Llama 3.1 70B Instruct or Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct ranks 164 of 187 models on sale for hard questions across science, maths and general knowledge, against 172 for Llama 3.1 70B Instruct.

Which is better for writing, Llama 3.1 70B Instruct or Llama 3.3 70B Instruct?

Llama 3.1 70B Instruct ranks 140 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 151 for Llama 3.3 70B Instruct.

Run Llama 3.1 70B Instruct and Llama 3.3 70B Instruct 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.