GPT-5.2 Pro vs Llama 3.2 1B Instruct
Llama 3.2 1B Instruct costs 835.8x less per output token than GPT-5.2 Pro ($0.201 vs $168.00 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $168.00
- Coding
- No data
- Overall
- 9.6
- Output $/M
- $0.201
GPT-5.2 Pro or Llama 3.2 1B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-5.2 Pro for a larger context window (400K against 60K tokens).
No benchmark has tested both yet. GPT-5.2 Pro has results on Epoch Capabilities Index, ARC-AGI and ARC-AGI-2; Llama 3.2 1B Instruct on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and LMArena Text: coding. Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Llama 3.2 1B Instruct has a AA Intelligence Index result, 4.8.
Directional only
Long documents
Listed context window
GPT-5.2 Pro
GPT-5.2 Pro takes 400K tokens against 60K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 3.2 1B Instruct
GPT-5.2 Pro $0.105, Llama 3.2 1B Instruct $0.0001 per turn.
List prices
At a glance
- Coding index
- GPT-5.2 Pro not benchmarked, Llama 3.2 1B Instruct not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- GPT-5.2 Pro $168.00 against Llama 3.2 1B Instruct $0.201 per million output tokens, 835.8x apart.
- Context window
- GPT-5.2 Pro takes 400K tokens, Llama 3.2 1B Instruct 60K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards measured
| Benchmark | GPT-5.2 Pro | Llama 3.2 1B Instruct | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | Not measured | 1.9% | Only Llama 3.2 1B Instruct measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 0.0% | Only Llama 3.2 1B Instruct measured |
| LMArena Text: coding | Not measured | 1070 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: software and IT | Not measured | 1056 | Only Llama 3.2 1B Instruct measured |
| Neither model has a result on the other 35 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | GPT-5.2 Pro | Llama 3.2 1B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 4.8 | Only Llama 3.2 1B Instruct measured |
| Epoch Capabilities Index | 156.3 | Not measured | Only GPT-5.2 Pro measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | GPT-5.2 Pro | Llama 3.2 1B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 0.0% | Only Llama 3.2 1B Instruct measured |
| BALROG | Not measured | 6.6% | Only Llama 3.2 1B Instruct measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 10.8% | Only Llama 3.2 1B Instruct measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index10 boards measured
| Benchmark | GPT-5.2 Pro | Llama 3.2 1B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 19.6% | Only Llama 3.2 1B Instruct measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 5.5% | Only Llama 3.2 1B Instruct measured |
| GPQA Diamond (Epoch AI run) | Not measured | 23.9% | Only Llama 3.2 1B Instruct measured |
| ARC-AGI | 90.5% | Not measured | Only GPT-5.2 Pro measured |
| ARC-AGI-2 | 54.2% | Not measured | Only GPT-5.2 Pro measured |
| SimpleBench | 57.4% | Not measured | Only GPT-5.2 Pro measured |
| Chess puzzles | 60.0% | Not measured | Only GPT-5.2 Pro measured |
| LMArena Text: hard prompts | Not measured | 1044 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: expert | Not measured | 1007 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: hard prompts in English | Not measured | 1087 | Only Llama 3.2 1B Instruct measured |
| Neither model has a result on the other 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards measured
| Benchmark | GPT-5.2 Pro | Llama 3.2 1B Instruct | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 0.0 | Only Llama 3.2 1B Instruct measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 0.0% | Only Llama 3.2 1B Instruct measured |
| OTIS Mock AIME | Not measured | 0.6% | Only Llama 3.2 1B Instruct measured |
| FrontierMath, tiers 1 to 3 | 74.0% | Not measured | Only GPT-5.2 Pro measured |
| FrontierMath, tier 4 | 46.0% | Not measured | Only GPT-5.2 Pro measured |
| LMArena Text: math | Not measured | 1086 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: mathematical work | Not measured | 1098 | Only Llama 3.2 1B Instruct measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | GPT-5.2 Pro | Llama 3.2 1B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 20.0% | Only Llama 3.2 1B Instruct measured |
| LMArena Text: science | Not measured | 1055 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: medicine and healthcare | Not measured | 1009 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: legal and government | Not measured | 1071 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: business and finance | Not measured | 1000 | Only Llama 3.2 1B Instruct measured |
| Neither model has a result on the other 13 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index14 boards measured
| Benchmark | GPT-5.2 Pro | Llama 3.2 1B Instruct | Leader |
|---|---|---|---|
| IFBench | Not measured | 22.8% | Only Llama 3.2 1B Instruct measured |
| Long context reasoning (AA-LCR) | Not measured | 6.7% | Only Llama 3.2 1B Instruct measured |
| LMArena Text | Not measured | 1055 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: instruction following | Not measured | 1031 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: creative writing | Not measured | 1033 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: English | Not measured | 1117 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: non-English | Not measured | 973 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: Chinese | Not measured | 959 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: German | Not measured | 1014 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: Russian | Not measured | 941 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: multi-turn | Not measured | 1030 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: longer queries | Not measured | 1050 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: writing and language | Not measured | 1030 | Only Llama 3.2 1B Instruct measured |
| LMArena Text: entertainment and media | Not measured | 1025 | Only Llama 3.2 1B Instruct measured |
| Neither model has a result on the other 32 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Llama 3.2 1B Instruct costs less
Repository review
50K input + 3K output tokens
Llama 3.2 1B Instruct costs less
Agent loop
200K input + 10K output tokens
Llama 3.2 1B Instruct costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5.2 Pro | Meta Llama 3.2 1B Instruct |
|---|---|---|
| Maker | OpenAI | Meta Llama |
| Weights | No public weights listed | Open weights |
| Released | December 10, 2025 | September 25, 2024 |
| Context window | 400K | 60K |
| Input $/Mtok | $21.00 | $0.027 |
| Output $/Mtok | $168.00 | $0.201 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2 Pro better than Llama 3.2 1B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-5.2 Pro for a larger context window (400K against 60K tokens).
Which is cheaper, GPT-5.2 Pro or Llama 3.2 1B Instruct?
GPT-5.2 Pro costs $21.00 per million input tokens and $168.00 per million output tokens; Llama 3.2 1B Instruct costs $0.027 and $0.201. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-5.2 Pro or Llama 3.2 1B Instruct?
GPT-5.2 Pro, with 400K tokens against 60K.
Has any benchmark tested both GPT-5.2 Pro and Llama 3.2 1B Instruct?
No benchmark has tested both yet. GPT-5.2 Pro has results on Epoch Capabilities Index, ARC-AGI and ARC-AGI-2; Llama 3.2 1B Instruct on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and LMArena Text: coding. Compare them on price and context instead. Data as of October 21, 2026.