Is Llama 3.2 3B Instruct a good deal?
Whether anything in this catalogue beats Llama 3.2 3B Instruct on both quality and price, and what you give up if it does. A computation on the current catalogue, not an opinion.
12 undominated of 144 · Nov 22, 2026
As of Nov 22, 2026, Llama 3.2 3B Instruct is dominated for Balanced on LMArena. DeepSeek V4 Flash 0423 scores 322.3 higher and costs 6% less, with a covering envelope. 12 of 144 rated, priced standard models are undominated.
Inspect model evidence Compare differences & requirements
DeepSeek V4 Flash 0423 is both better and cheaper than Llama 3.2 3B Instruct: 322.3 points higher on LMArena and 6% less per million tokens, $0.0075 cheaper at this mix.
LMArena Elo · higher is better
Scale starts at 1040 Elo
1109.6
Effective $/M · Balanced · lower is better
$0.120/M
LMArena Elo · higher is better
Scale starts at 1040 Elo
1431.9
Effective $/M · Balanced · lower is better
$0.113/M
Llama 3.2 3B Instruct takes text, returns up to 117,964 tokens from a 131,072-token context, and is listed by 1 seller.
Compared against 144 rated, priced models on this lens: 6 models dominate it and give up nothing, 5 more dominate it but give something up. Llama 3.2 3B Instruct scores 1109.6 at $0.120 per million tokens for this mix.
Envelope-safe replacements
Each row scores at least as high, costs no more, and covers this model’s context, output, modalities, tools, and reasoning. A cheaper narrower model is not listed here.
| Model | LMArena | Effective $/M | You save |
|---|---|---|---|
| DeepSeek V4 Flash 0423 | 1431.9 +322.3 | $0.113/M | 6% |
| gpt-oss-120b | 1365.4 +255.8 | $0.060/M | 50% |
| Gemma 3 27B | 1357.8 +248.2 | $0.100/M | 17% |
| Granite 4.2 8B | 1318.8 +209.2 | $0.083/M | 31% |
| Gemma 3 4B | 1290.8 +181.2 | $0.043/M | 65% |
| gpt-oss-20b | 1287.6 +178.0 | $0.034/M | 72% |
Higher score, lower price, named losses
Not a drop-in. The loss is why these are not a recommendation.
| Model | LMArena | Effective $/M | You give up |
|---|---|---|---|
| Qwen3.5-Flash | 1397.1 | $0.114/M | max output |
| Gemma 3 12B | 1334.2 | $0.075/M | max output |
| Mistral Small 3 | 1233.6 | $0.058/M | context, max output |
| Nova Lite 1.0 | 1228.5 | $0.105/M | max output |
| Phi 4 | 1216.7 | $0.088/M | context, max output |
The link keeps the model and mix, using the current catalogue. Monthly spend and switching cost stay in this browser tab and are left out of the link.
Saved decision references
Save the model, workload, catalogue date and capability-preservation rule in this browser. Spend, switching cost and bill contents are not saved. No account or notifications.
Constraint: replacements must preserve the model’s capabilities; any losses remain named trade-offs.
Historical decisions cannot be fully replayed from saved references: past prices, scores and capability evidence are not stored.