Across 3 comparable benchmarks, Llama3.1-405B Instruct and Amazon Nova Pro are evenly matched at 1 apiece.
Moderate evidence3 of 3 shared results countedHow we compare
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | Llama3.1-405B Instruct | Amazon Nova Pro |
|---|---|---|
| Context window | 128K tokens | 300K tokens |
| Input / 1M | $2.40 | $0.800 |
| Output / 1M | $2.40 | $3.20 |
| Blended (4:1) | $2.40 | $1.28 |
| Status | Available | Available |
| Released | July 23, 2024 | December 3, 2024 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 2 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Tied on 1 counted
Amazon Nova Pro ahead on 1 of 1 counted
No shared comparable results for Abstract reasoning, Science & health, Computer & tool use, Research & search, Long context, Multimodal, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show Llama3.1-405B Instruct relative to Amazon Nova Pro. Reading the results
| Benchmark | Llama3.1-405B Instruct | Amazon Nova Pro | Gap |
|---|---|---|---|
| HumanEvalCode Generation & Editing · Accuracy | 89.0Normal · no tools | 89.0Normal · no tools | =#18 vs #18 of 100 |
| MATHMathematics · Accuracy | 73.9Normal · no tools | 76.6Normal · no tools | −2.7 pts#17 vs #14 of 42 |
| MMLUKnowledge Exams · Accuracy | 88.6Normal · no tools | 85.9Normal · no tools | +2.7 pts#14 vs #31 of 114 |
A dash means no result is available.
| Benchmark | Llama3.1-405B Instruct | Amazon Nova Pro |
|---|---|---|
| GPQA Diamond | 49.0 | — |
| HLE | — | 4.4 |
| MMLU-Pro | 73.4 | — |
| LiveCodeBench | 30.2 | — |
| MBPP | 88.6 | — |
| Terminal Bench Hard | — | 6.1 |
| ECI | — | 124 |
| Creative Writing | 868 | — |
| MMMU | — | 62.0 |
| MMMU-Pro | — | 44.3 |
| BBH | 89.2 | — |
| SimpleBench | 23.0 | — |
| SimpleQA | 17.1 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Llama3.1-405B Instruct costs87%morethan Amazon Nova Pro per million tokens.Using listed rates vs standard rates at this token mix.
Llama3.1-405B Instruct: Listed text rates; pricing tier not confirmed.
Amazon Nova Pro: Standard pricing. AWS Bedrock official pricing (Amazon Nova Pro; US East N. Virginia) verified 2026-11-14
| Price / 1M tokens | Llama3.1-405B Instruct | Amazon Nova Pro | Ratio |
|---|---|---|---|
| Input | $2.40 | $0.80 | 3.00× |
| Output | $2.40 | $3.20 | 0.75× |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | $2.40 | $1.28 | 1.88× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
| Attribute | Llama3.1-405B Instruct | Amazon Nova Pro |
|---|---|---|
| Availability | Available | Available |
| Provider | Facebook AI Research Lab | Amazon |
| Model type | Foundation model | Multimodal model |
| First release | July 23, 2024 | December 3, 2024 |
| Context window | 128K tokens | 300K tokens |
| Total parameters | 405B | — |
| Architecture | Dense | Undisclosed |
| Documented capabilities | — | Multilingual |
| Weights | Open weights | Closed / API only |
| Licence | LLAMA 3.1 COMMUNITY LICENSE AGREEMENT | — |
| Commercial use | Commercial use allowed | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Llama3.1-405B Instruct or Amazon Nova Pro? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.