Multi-dimensional Model & Plan Comparison
Compare pricing, coding pass rates, context windows, and estimated monthly invoices side-by-side. Generate shareable posters with 1 click.
Popular Comparisons:
MetaVerified
Llama 4 Scout
★ Save 92% ★ Massive Context 10M
Input$0.11 / 1M
Output$0.34 / 1M
Context10M
CursorBench Pass Rate—
Pick your workflow, then your budget
Estimates use our price snapshot, excluding cache, retries, taxes and tools. Check availability for preview and legacy models.
Workload cost · USD (lower costs less)
Llama 3.1 405B$21.60
Llama 4 Scout$1.78
Llama 4 Maverick$3.96
Context capacity · tokens (not recall accuracy)
Llama 3.1 405B128,000
Llama 4 Scout10,000,000
Llama 4 Maverick1,000,000
CursorBench 4.0 · %
Llama 3.1 405BNo verified data
Llama 4 ScoutNo verified data
Llama 4 MaverickNo verified data
Tool reliability, long-context recall and same-harness SWE-bench: untested, not zero.
CursorBench · 2026-10-07 ↗Patch review example: why does an empty array slip through?
Editorial example, not measured model output. Review boundary contracts and regression tests; this is not a model ranking.
export function mean(values: number[]) {
return values.reduce((a, b) => a + b, 0)
/ values.length;
}
// mean([]) => NaN
// Missing an explicit empty-input contract⚙️ Select ModelLlama 3.1 405B vs Llama 4 Scout vs Llama 4 Maverick
Slot 1Meta
Slot 2Meta
Slot 3Meta
💰 Monthly Cost Simulation
Simulate monthly cost differences based on your estimated token usage volume
Llama 3.1 405B
$21.60/ mo
(in: $18.00 + out: $3.60)
Llama 4 Scout
$1.78/ mo
(in: $1.10 + out: $0.68)
Llama 4 Maverick
$3.96/ mo
(in: $2.20 + out: $1.76)
| Attribute | Llama 3.1 405BMeta | Llama 4 ScoutMeta | Llama 4 MaverickMeta |
|---|---|---|---|
| Input | $1.80 | $0.11 | $0.22 |
| Output | $1.80 | $0.34 | $0.88 |
| Context | 128K | 10M | 1M |
| CursorBench Pass Rate | — | — | — |
| Status | Verified | Verified | Verified |
| Tags & Capabilities | Open weights, Frontier | Fast, Low cost, Vision, Open source, Long context | Workhorse, Vision, Open source, Long context |
| LMArena Code | #— | #— | #— |
| LMArena Agent | #— | #— | #— |
| CursorBench | #— | #— | #— |
| Artificial Analysis | #87 | #95 | #78 |
| Vals AI | #— | #— | #— |
| LiveBench | #— | #— | #— |
| LMArena Text | #77 | #— | #— |