Enter opens the highlighted result. Esc closes.

Ministral 3 3B 2512 vs Llama 3 8B Lunaris

Llama 3 8B Lunaris costs 2.0x less per output token than Ministral 3 3B 2512 ($0.05 vs $0.10 per million). Updated October 23, 2026; no benchmark has tested both models yet.

Replace Ministral 3 3B 2512 Replace Llama 3 8B Lunaris
Ministral 3 3B 2512Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.10
S Llama 3 8B LunarisSao10K
Coding
No data
Overall
No data
Output $/M
$0.05
vs $0.10 vs $0.05 per 1M output tokens. Llama 3 8B Lunaris is 2.0x cheaper.

Ministral 3 3B 2512 or Llama 3 8B Lunaris: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Ministral 3 3B 2512 for a larger context window (131K against 8K tokens).

Model AMinistral 3 3B 2512Mistral AINot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 3 8B LunarisSao10KNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Ministral 3 3B 2512 has results on AA Coding Index, AA Intelligence Index and AA Agentic Index; Llama 3 8B Lunaris has none yet. 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.

At a glance

Coding index
Ministral 3 3B 2512 not benchmarked, Llama 3 8B Lunaris 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
Ministral 3 3B 2512 $0.10 against Llama 3 8B Lunaris $0.05 per million output tokens, 2.0x apart.
Context window
Ministral 3 3B 2512 takes 131K tokens, Llama 3 8B Lunaris 8K.

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 Index1 board measured
Coding benchmarks for Ministral 3 3B 2512 and Llama 3 8B Lunaris
BenchmarkMinistral 3 3B 2512Llama 3 8B LunarisLeader
AA Coding Index4.8Not measuredOnly Ministral 3 3B 2512 measured
Neither model has a result on the other 42 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Intelligence benchmarks for Ministral 3 3B 2512 and Llama 3 8B Lunaris
BenchmarkMinistral 3 3B 2512Llama 3 8B LunarisLeader
AA Intelligence Index4.8Not measuredOnly Ministral 3 3B 2512 measured
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Agentic work benchmarks for Ministral 3 3B 2512 and Llama 3 8B Lunaris
BenchmarkMinistral 3 3B 2512Llama 3 8B LunarisLeader
AA Agentic Index0.8Not measuredOnly Ministral 3 3B 2512 measured
Neither model has a result on the other 41 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
Web design benchmarks for Ministral 3 3B 2512 and Llama 3 8B Lunaris
BenchmarkMinistral 3 3B 2512Llama 3 8B LunarisLeader
Design Arena: websites1027Not measuredOnly Ministral 3 3B 2512 measured
Design Arena: game dev948Not measuredOnly Ministral 3 3B 2512 measured
Design Arena: 3D963Not measuredOnly Ministral 3 3B 2512 measured
Design Arena: all code categories1009Not measuredOnly Ministral 3 3B 2512 measured
Neither model has a result on the other 5 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

Ministral 3 3B 2512$0.0001Fits in one request
Llama 3 8B Lunaris$0.0001Fits in one request

Llama 3 8B Lunaris costs less

Repository review

50K input + 3K output tokens

Ministral 3 3B 2512$0.0053Fits in one request
Llama 3 8B Lunaris$0.0022Exceeds the context window

Llama 3 8B Lunaris costs less

Agent loop

200K input + 10K output tokens

Ministral 3 3B 2512$0.021Exceeds the context window
Llama 3 8B Lunaris$0.0085Exceeds the context window

Llama 3 8B Lunaris 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.

Specifications of Ministral 3 3B 2512 and Llama 3 8B Lunaris
SpecificationMistral Ministral 3 3B 2512Sao10K Llama 3 8B Lunaris
MakerMistral AISao10K
WeightsOpen weightsOpen weights
ReleasedDecember 2, 2025August 13, 2024
Context window131K8K
Input $/Mtok$0.10$0.04
Output $/Mtok$0.10$0.05
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Ministral 3 3B 2512 better than Llama 3 8B Lunaris for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Ministral 3 3B 2512 for a larger context window (131K against 8K tokens).

Which is cheaper, Ministral 3 3B 2512 or Llama 3 8B Lunaris?

Ministral 3 3B 2512 costs $0.10 per million input tokens and $0.10 per million output tokens; Llama 3 8B Lunaris costs $0.04 and $0.05. Cost per solved task is known for neither of them.

Which has the bigger context window, Ministral 3 3B 2512 or Llama 3 8B Lunaris?

Ministral 3 3B 2512, with 131K tokens against 8K.

Has any benchmark tested both Ministral 3 3B 2512 and Llama 3 8B Lunaris?

No benchmark has tested both yet. Ministral 3 3B 2512 has results on AA Coding Index, AA Intelligence Index and AA Agentic Index; Llama 3 8B Lunaris has none yet. Compare them on price and context instead. Data as of October 23, 2026.

Compare next