Llama 3.2 Instruct 3B
Context 128K tokens
Top 2 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Price channel | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Parasailvia OpenRouter — Price via OpenRouter: OpenRouter's price for Parasail's endpoint (https://openrouter.ai/meta-llama/llama-3.2-3b-instruct/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Parasail's endpoint (https://openrouter.ai/meta-llama/llama-3.2-3b-instruct/providers), collected 2026-11-03. | $0.050 | $0.330 | |
| 2 | Cloudflarevia OpenRouter — Price via OpenRouter: OpenRouter's price for Cloudflare's endpoint (https://openrouter.ai/meta-llama/llama-3.2-3b-instruct/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Cloudflare's endpoint (https://openrouter.ai/meta-llama/llama-3.2-3b-instruct/providers), collected 2026-11-03. | $0.051 | $0.335 |
Composite
1 of 7 inputs6 radar axes: DesignArena's two boards share one1.7
Thin data · 1/7Based on only 1 of 7 Composite inputs — treat this rank as uncertainAA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 2.3AA Agentic —Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
10 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Efficiency
GPQA Diamond (OpenRouter run) — measured cost per task98$0.00015
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 → · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
Instruction-following
IFBench (AA single-turn)926.2%
IFBench (AA single-turn) published 2026-09-10 → · Published board — Tests precise single-turn instructions with deterministic rule checks.
LisanBench word chains, v0.2.0 (Lisan al Gaib)28.00
LisanBench word chains, v0.2.0 (Lisan al Gaib) v0.2.0 → · Published board — A model builds the longest chain of English words it can, each differing from the last by one letter, with no repeats and only dictionary words, from 50 starting words; any broken rule ends the chain.
Knowledge
Humanity's Last Exam (AA text-only)345.3%
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
Long-context
AA-LCR v1.1124.3%
AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA)53.3%
AIME 2025 (AA) v2025 → · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Science
GPQA Diamond (AA)225.5%
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)011.6%
GPQA Diamond (OpenRouter run) published 2026-09-15 → · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Tool-use
τ²-Bench Telecom (AA)2121.1%
τ²-Bench Telecom (AA) published 2026-09-10 → · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.
Writing
EQ-Bench Creative Writing v35594 Elo
EQ-Bench Creative Writing v3 v3 → · Published board — A LLM-judged creative writing benchmark with vocabulary and GPT-slop controls.
Unusual results
1 threshold-crossing signal flagged · 10 eligible benchmark families
How flags are calculated
Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.
- unusually weak GPQA Diamond (OpenRouter run) published 2026-09-15
Why
Observed: 0.11616 fractionPeer mean 0.75171 · peer sd 0.1629 · n 122 · families 122Directed z -3.901 · baseline z -1.076 · gap -2.825 · profile n 90.11616 fractionmeasured· 198 tasks· 0 USD per task (measured by OpenRouter)observed 2026-09-15openrouter.ai ↗Evidence
Axis: GPQA Diamond (OpenRouter run) · published 2026-09-15 · Published boardExact value:0.116162fractionTasks evaluated: 198Published mean cost: 0.0001537979797979798 USD per task (measured by OpenRouter) — measured by OpenRouter on GPQA Diamond (OpenRouter run)Observed: 2026-09-15T23:29:03.209Z · publication date: not recordedObservation id:openrouter:meta-llama/llama-3.2-3b-instruct|gpqa_diamondSource: https://openrouter.ai/benchmarks
Missing coverage · 309 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Token offers by platform · 2 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
2 offers within the active global filters; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
OpenRouter (2)
Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/meta-llama/llama-3.2-3b-instruct/providers, collected 2026-11-03.
| Parasail | globalparasail/bf16 | $0.050 raw in $/1M | $0.330 raw out $/1M | |
| Cloudflare | globalcloudflare | $0.051 raw in $/1M | $0.335 raw out $/1M |