Skip to main content

Model comparison

Llama 3.1 405B vs Llama 4 Maverick

Data verified

Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

51.71/100
Margin
28.2pts
← winning
23.49/100
0 category wins0 category wins

Public leaderboard positions: Llama 3.1 405B #102 (Estimated); Llama 4 Maverick #191 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Llama 3.1 405B and Llama 4 Maverick share 11 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to Llama 3.1 405B; 7 to Llama 4 Maverick.

Updated July 20, 2026
Shared results
11
Llama 3.1 405B only
0
Llama 4 Maverick only
7
Comparable categories
0 / 8

Benchmark data for Llama 3.1 405B and Llama 4 Maverick is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Llama 4 Maverick has the larger context window at 1M, compared with 128K for Llama 3.1 405B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Llama 3.1 405B and Llama 4 Maverick
CategoryLlama 3.1 405BΔLlama 4 Maverick
MathLlama 3.1 405BNot measuredMarginNo overlapLlama 4 Maverick0.7

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricLlama 3.1 405BLlama 4 MaverickComparison
Input / output priceUSD per 1M tokensLlama 3.1 405B$0 input / $0 outputLlama 4 Maverick$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondLlama 3.1 405B29 tok/sLlama 4 Maverick121 tok/sLlama 4 Maverick has the higher measured throughput.
First-answer latencyseconds to first tokenLlama 3.1 405B2.19 sLlama 4 Maverick0.95 sLlama 4 Maverick reaches the first token sooner.
Context windowmaximum listed tokensLlama 3.1 405B128KLlama 4 Maverick1MLlama 4 Maverick lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkLlama 3.1 405BLlama 4 MaverickResult
τ²-bench resultsSource 19%17.8%Llama 3.1 405B leads
AA Agentic IndexSource 1.3%Not comparable
GDPval-AASource 0.0%Not comparable
GDPval-AASource -16Not comparable
Coding
BenchmarkLlama 3.1 405BLlama 4 MaverickResult
AA-SciCodeSource 29.9%33.1%Llama 4 Maverick leads
AA Coding IndexSource 16.3%Not comparable
Reasoning
BenchmarkLlama 3.1 405BLlama 4 MaverickResult
AA-LCRSource 24.3%46.0%Llama 4 Maverick leads
CritPtSource 0.0%0.0%Tie
Knowledge
BenchmarkLlama 3.1 405BLlama 4 MaverickResult
Artificial Analysis Intelligence IndexSource 8.5%14.3%Llama 4 Maverick leads
AA-GPQA DiamondSource 51.5%67.1%Llama 4 Maverick leads
AA-HLESource 4.2%4.8%Llama 4 Maverick leads
AA-Omniscience IndexSource -17.3%-41.8%Llama 3.1 405B leads
AA-Omniscience AccuracySource 22.3%24.3%Llama 4 Maverick leads
AA-Omniscience Hallucination RateSource 51.0%87.3%Llama 3.1 405B leads
Math
BenchmarkLlama 3.1 405BLlama 4 MaverickResult
FrontierMath v2 (Tiers 1-3)Source 0.690%Not comparable
Multimodal
BenchmarkLlama 3.1 405BLlama 4 MaverickResult
AA-MMMU-ProSource 62.1%Not comparable
Design Arena WebsiteSource 903Not comparable
Inst. Following
BenchmarkLlama 3.1 405BLlama 4 MaverickResult
AA-IFBenchSource 39.0%43.0%Llama 4 Maverick leads
Frequently Asked Questions (3)

Can I compare Llama 3.1 405B and Llama 4 Maverick on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Llama 3.1 405B and Llama 4 Maverick today?

Llama 3.1 405B: $0.00 input / $0.00 output per 1M tokens Llama 4 Maverick: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Llama 3.1 405B
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Llama 4 Maverick
API / mo$0
Self-host / mo$2,610
Break-even
Model the full break-even

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.